Triple
T7295600
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Black Prince's Ruby |
E164512
|
entity |
| Predicate | positionInCrown |
P52685
|
FINISHED |
| Object | front cross above the Cullinan II diamond |
—
|
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: front cross above the Cullinan II diamond | Statement: [Black Prince's Ruby, positionInCrown, front cross above the Cullinan II diamond]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionInCrown Context triple: [Black Prince's Ruby, positionInCrown, front cross above the Cullinan II diamond]
-
A.
crownPosition
chosen
Indicates the relative placement or orientation of a crown with respect to another object or reference point.
-
B.
positionDuringCoronation
Indicates the specific role, title, or office an entity held at the time of a coronation event.
-
C.
positionWithinCastle
Indicates that one entity is located inside the spatial boundaries of a castle.
-
D.
hasCrownCount
Indicates the number of crowns that an entity possesses or is associated with.
-
E.
crownedWith
Indicates that one entity serves as a crown, top, or decorative upper covering placed upon another entity.
- 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_69c6887a499881909dd23341399c59d8 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6eb8d0c6c8190b32cd08b9a5d96cc |
completed | March 27, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69c6e76c5fbc8190b378830082f11cb0 |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 3 p.m.