Triple
T7154784
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Société Anonyme |
E166781
|
entity |
| Predicate | capitalDivision |
P75182
|
FINISHED |
| Object | capital divided into shares |
—
|
LITERAL FINISHED |
How this triple was built (2 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: capital divided into shares | Statement: [Société Anonyme, capitalDivision, capital divided into shares]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capitalDivision Context triple: [Société Anonyme, capitalDivision, capital divided into shares]
-
A.
divisionTitle
Indicates the formal name or title assigned to a specific division within a larger organization or structure.
-
B.
politicalDivision
Indicates that one entity is a governmental or administrative subdivision or jurisdiction within the territory or authority of another entity.
-
C.
regionDivision
Indicates a hierarchical or organizational subdivision relationship where one region is partitioned into smaller constituent regions.
-
D.
capitalDividedInto
Indicates that the capital city is partitioned into distinct administrative or geographic subdivisions.
-
E.
divisionSince
Indicates that one entity has been divided or split from another starting at a specific point in time.
- F. None of above. chosen
Provenance (4 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_69c68887a5cc8190bec0ea96227164f7 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e80c747c8190a017a2b1c3e78a3f |
completed | March 27, 2026, 8:26 p.m. |
| PD | Predicate disambiguation | batch_69c6e1caf4e48190b47bb398a3c1554d |
completed | March 27, 2026, 8 p.m. |
| PDg | Predicate description generation | batch_69c6e4a213508190a40aca39f9eee7d5 |
completed | March 27, 2026, 8:12 p.m. |
Created at: March 27, 2026, 2:46 p.m.