Triple
T8854645
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Château de Vincennes |
E210723
|
entity |
| Predicate | heightOfKeep |
P9788
|
FINISHED |
| Object | approximately 50 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 50 meters | Statement: [Château de Vincennes, heightOfKeep, approximately 50 meters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heightOfKeep Context triple: [Château de Vincennes, heightOfKeep, approximately 50 meters]
-
A.
heightAboveSurroundings
Indicates that an entity’s vertical position or elevation is higher than that of its immediate surrounding area.
-
B.
hasHeight
chosen
Indicates that one entity possesses a specific vertical measurement or stature.
-
C.
dropHeight
Indicates the vertical distance from which an object is released or allowed to fall.
-
D.
cargoHoldHeight
Indicates the vertical interior dimension or clearance height of a cargo hold space.
-
E.
heightReference
Indicates that one entity’s height is being measured, compared, or defined relative to another specified reference point or standard.
- 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_69ca838a424c8190b1ecac115c2927e7 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc60c6dce88190b175698b191fb89b |
completed | April 1, 2026, 12:03 a.m. |
| PD | Predicate disambiguation | batch_69cc5c25b874819084c9ba391703e066 |
completed | March 31, 2026, 11:43 p.m. |
Created at: March 30, 2026, 6:49 p.m.