Triple
T9838059
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SPOT Earth observation satellites |
E239151
|
entity |
| Predicate | dataDistributedBy |
P64619
|
FINISHED |
| Object |
SPOT Image
SPOT Image is a commercial company that specializes in distributing high-resolution Earth observation imagery and related geospatial products derived from the SPOT satellite constellation.
|
E824049
|
NE FINISHED |
How this triple was built (5 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: SPOT Image | Statement: [SPOT Earth observation satellites, dataDistributedBy, SPOT Image]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SPOT Image Context triple: [SPOT Earth observation satellites, dataDistributedBy, SPOT Image]
-
A.
USGS EarthExplorer
USGS EarthExplorer is an online search, discovery, and download platform operated by the U.S. Geological Survey that provides public access to a wide range of satellite imagery and geospatial datasets.
-
B.
SPOT Earth observation satellites
SPOT Earth observation satellites are a series of French-led remote sensing spacecraft that provide high-resolution optical imagery of Earth for applications such as mapping, environmental monitoring, and land-use analysis.
-
C.
Pacific Data Images
Pacific Data Images is an American computer animation and visual effects studio best known as a key division of DreamWorks Animation, contributing to numerous major animated films.
-
D.
Operational Land Imager
The Operational Land Imager is a multispectral imaging sensor on Landsat 8 designed to capture high-resolution, calibrated images of Earth’s land surfaces for environmental monitoring and land-use analysis.
-
E.
Landsat 8
Landsat 8 is an Earth observation satellite in the long-running Landsat program, providing high-resolution multispectral imagery for environmental monitoring, land use analysis, and climate research.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: SPOT Image Triple: [SPOT Earth observation satellites, dataDistributedBy, SPOT Image]
Generated description
SPOT Image is a commercial company that specializes in distributing high-resolution Earth observation imagery and related geospatial products derived from the SPOT satellite constellation.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: SPOT Image Target entity description: SPOT Image is a commercial company that specializes in distributing high-resolution Earth observation imagery and related geospatial products derived from the SPOT satellite constellation.
-
A.
USGS EarthExplorer
USGS EarthExplorer is an online search, discovery, and download platform operated by the U.S. Geological Survey that provides public access to a wide range of satellite imagery and geospatial datasets.
-
B.
SPOT Earth observation satellites
SPOT Earth observation satellites are a series of French-led remote sensing spacecraft that provide high-resolution optical imagery of Earth for applications such as mapping, environmental monitoring, and land-use analysis.
-
C.
Pacific Data Images
Pacific Data Images is an American computer animation and visual effects studio best known as a key division of DreamWorks Animation, contributing to numerous major animated films.
-
D.
Operational Land Imager
The Operational Land Imager is a multispectral imaging sensor on Landsat 8 designed to capture high-resolution, calibrated images of Earth’s land surfaces for environmental monitoring and land-use analysis.
-
E.
Landsat 8
Landsat 8 is an Earth observation satellite in the long-running Landsat program, providing high-resolution multispectral imagery for environmental monitoring, land use analysis, and climate research.
- F. None of above. chosen
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dataDistributedBy Context triple: [SPOT Earth observation satellites, dataDistributedBy, SPOT Image]
-
A.
isDistributedThrough
chosen
Indicates that something is supplied, circulated, or made available to others via a particular channel, medium, or distribution mechanism.
-
B.
distributionBy
Indicates how something is allocated, arranged, or spread according to a specified criterion or grouping.
-
C.
distributesIn
Indicates that one entity allocates or hands out something (e.g., items, resources, information) within or across a specified area, group, or context.
-
D.
distributedAs
Indicates that something is allocated, delivered, or spread out according to a particular pattern, rule, or distribution scheme.
-
E.
distributionHub
Indicates a location or facility that serves as a central point for receiving, sorting, and redistributing goods or resources to multiple destinations.
- F. None of above.
Provenance (6 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ca84e314108190978324a4bdb959f8 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb347ff4c81908c312548a25bae71 |
completed | April 2, 2026, 12:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1d5d145ac8190ad10a4328216ef54 |
completed | April 5, 2026, 3:24 a.m. |
| NEDg | Description generation | batch_69d1d6bb23cc81909efbeccf147018e8 |
completed | April 5, 2026, 3:27 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d1d726e58c819090135d1ff275d2d8 |
completed | April 5, 2026, 3:29 a.m. |
| PD | Predicate disambiguation | batch_69cd03e30bc08190816c0a6d29c21b0f |
completed | April 1, 2026, 11:39 a.m. |
Created at: March 30, 2026, 8:33 p.m.