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.