Triple
T33916577
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coach Jack Reilly |
E869475
|
entity |
| Predicate | rivalOfCharacter |
P22658
|
FINISHED |
| Object | Gordon Bombay |
—
|
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: Gordon Bombay | Statement: [Coach Jack Reilly, rivalOfCharacter, Gordon Bombay]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rivalOfCharacter Context triple: [Coach Jack Reilly, rivalOfCharacter, Gordon Bombay]
-
A.
rivalOwnedByCharacter
Indicates that a rival entity is owned, controlled, or possessed by a specific character.
-
B.
rivalOf
chosen
Indicates a relationship in which two entities compete against or oppose each other, often seeking advantage in the same domain or objective.
-
C.
fictionalRivalOf
Indicates a rivalry relationship that exists between two entities only within a fictional or narrative context.
-
D.
bearerRivalOf
Indicates that the bearer is in a state of rivalry or competitive opposition with the related entity.
-
E.
rivalryCharacterization
Indicates a relationship in which two entities are characterized as rivals, typically defined by ongoing competition, opposition, or conflict between them.
- 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_69f3499869bc8190b6c33a81686af226 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7064e906881909c3186c646145d34 |
completed | May 3, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69f70100ec1c8190a6b97f50e88891f2 |
completed | May 3, 2026, 8:02 a.m. |
Created at: May 1, 2026, 1:48 a.m.