Triple
T4279517
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PostGIS |
E97115
|
entity |
| Predicate | supportsFormat |
P203
|
FINISHED |
| Object |
WKT
WKT (Well-Known Text) is a text-based markup language used to represent vector geometry objects such as points, lines, and polygons in geographic information systems.
|
E427692
|
NE FINISHED |
How this triple was built (4 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: WKT | Statement: [PostGIS, supportsFormat, WKT]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: WKT Context triple: [PostGIS, supportsFormat, WKT]
-
A.
KML
KML (Keyhole Markup Language) is an XML-based file format used to display geographic data and annotations in mapping applications such as Google Earth and Google Maps.
-
B.
WFS
WFS (Web Feature Service) is an OGC standard web service that provides access to and manipulation of geographic features over the internet in vector form.
-
C.
JTS
JTS is a leading academic and spiritual center of Conservative Judaism, known for training rabbis, cantors, and scholars and for its influential research in Jewish studies.
-
D.
KWT
KWT is the three-letter ISO 3166-1 alpha-3 country code assigned to Kuwait.
-
E.
OGC
OGC is the Office of General Counsel within the Office of Justice Programs, providing legal advice and services on justice-related programs and policies.
- 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: WKT Triple: [PostGIS, supportsFormat, WKT]
Generated description
WKT (Well-Known Text) is a text-based markup language used to represent vector geometry objects such as points, lines, and polygons in geographic information systems.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: WKT Target entity description: WKT (Well-Known Text) is a text-based markup language used to represent vector geometry objects such as points, lines, and polygons in geographic information systems.
-
A.
KML
KML (Keyhole Markup Language) is an XML-based file format used to display geographic data and annotations in mapping applications such as Google Earth and Google Maps.
-
B.
WFS
WFS (Web Feature Service) is an OGC standard web service that provides access to and manipulation of geographic features over the internet in vector form.
-
C.
JTS
JTS is a leading academic and spiritual center of Conservative Judaism, known for training rabbis, cantors, and scholars and for its influential research in Jewish studies.
-
D.
KWT
KWT is the three-letter ISO 3166-1 alpha-3 country code assigned to Kuwait.
-
E.
OGC
OGC is the Office of General Counsel within the Office of Justice Programs, providing legal advice and services on justice-related programs and policies.
- F. None of above. chosen
Provenance (5 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_69b34544be3c819084d1ab82d29f90c5 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b350367da48190b735deef9b5d2d2e |
completed | March 12, 2026, 11:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5b7b708b481908c1683741f84ee55 |
completed | March 14, 2026, 7:32 p.m. |
| NEDg | Description generation | batch_69b5bb84ed808190891f2a75296c11c6 |
completed | March 14, 2026, 7:48 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b5bc392228819089fe64b55bb572cc |
completed | March 14, 2026, 7:51 p.m. |
Created at: March 12, 2026, 11:07 p.m.