Triple
T27991416
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gary Caldwell |
E706887
|
entity |
| Predicate | playedInDerbyOrRivalry |
P44174
|
FINISHED |
| Object | Old Firm derbies with Rangers while at Celtic |
—
|
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: Old Firm derbies with Rangers while at Celtic | Statement: [Gary Caldwell, playedInDerbyOrRivalry, Old Firm derbies with Rangers while at Celtic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: playedInDerbyOrRivalry Context triple: [Gary Caldwell, playedInDerbyOrRivalry, Old Firm derbies with Rangers while at Celtic]
-
A.
playsInDerby
chosen
Indicates participation by an entity as a competitor or performer in a derby event.
-
B.
playsInDerbyWith
Indicates that two entities participate together as opponents or competitors in the same derby event or match.
-
C.
hasHomeStadiumInRivalry
Indicates that one entity’s home stadium is the venue used when it participates in a rivalry with another entity.
-
D.
associatedWithRivalryGame
Indicates that there is a connection or involvement between entities specifically in the context of a rivalry game.
-
E.
playsRivalryGameAgainst
Indicates that one entity participates in a rivalry game as an opponent against 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_69ef96b8b8d88190bad5e4ae966bf14e |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69f6db1f3ec48190a82e7d893d3c76ba |
completed | May 3, 2026, 5:20 a.m. |
| PD | Predicate disambiguation | batch_69f6d82adfa481908a5e196d2e18c73f |
completed | May 3, 2026, 5:07 a.m. |
Created at: April 27, 2026, 7:50 p.m.