Triple
T26410742
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Château de Coucy |
E663951
|
entity |
| Predicate | diameterOfKeep |
P45548
|
FINISHED |
| Object | approximately 31 meters |
—
|
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: approximately 31 meters | Statement: [Château de Coucy, diameterOfKeep, approximately 31 meters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: diameterOfKeep Context triple: [Château de Coucy, diameterOfKeep, approximately 31 meters]
-
A.
bodyDiameter
Indicates the measurement of how wide an object's body is across its broadest cross-section.
-
B.
approximateDiameter
Indicates that one entity specifies the estimated or rough measurement of another entity’s diameter.
-
C.
arenaDiameter
Indicates the diameter measurement of an arena, typically the straight-line distance across it through its center.
-
D.
houseDiameter
Indicates the measured diameter or widest straight-line span of a house.
-
E.
structureDiameter
chosen
Indicates the measured diameter or width of a given structure.
- F. None of above.
Provenance (3 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_69ee883931888190901be96d75ee23cc |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69f6113143f481909c64dfc1975e3a59 |
completed | May 2, 2026, 2:58 p.m. |
| PD | Predicate disambiguation | batch_69f5f800fa9c8190aab0962669fde8ac |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 11:37 p.m.