Triple
T31357301
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bon Accord F.C. |
E799770
|
entity |
| Predicate | opponentInRecordDefeat |
P149397
|
FINISHED |
| Object | Arbroath F.C. |
—
|
NE NERFINISHED |
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: Arbroath F.C. | Statement: [Bon Accord F.C., opponentInRecordDefeat, Arbroath F.C.]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: opponentInRecordDefeat Context triple: [Bon Accord F.C., opponentInRecordDefeat, Arbroath F.C.]
-
A.
defeatedBy
Indicates that one entity has been beaten, overcome, or conquered by another in a contest, conflict, or competition.
-
B.
largestDefeatOpponent
chosen
Indicates that one entity experienced its most significant loss or defeat at the hands of the specified opponent.
-
C.
sideDefeated
Indicates that one side in a conflict, competition, or contest has been beaten or overcome by another side.
-
D.
defeatedInEvent
Indicates that one entity lost to another entity in the context of a specific event or competition.
-
E.
surrenderedOpponent
Indicates that one entity yielded or gave up in favor of another entity, recognizing the other as its opponent.
- 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_69f224e5e9bc8190a16339328897c4f8 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6b49436b0819094e21603054d05d4 |
completed | May 3, 2026, 2:36 a.m. |
| PD | Predicate disambiguation | batch_69f6b3a7bdb481908d16a32f49e38c2c |
completed | May 3, 2026, 2:32 a.m. |
Created at: April 29, 2026, 9:17 p.m.