Triple
T6955898
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michonne |
E161241
|
entity |
| Predicate | speciesOpponents |
P66530
|
FINISHED |
| Object | walkers (zombies) |
—
|
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: walkers (zombies) | Statement: [Michonne, speciesOpponents, walkers (zombies)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: speciesOpponents Context triple: [Michonne, speciesOpponents, walkers (zombies)]
-
A.
rivalOf
Indicates a relationship in which two entities compete against or oppose each other, often seeking advantage in the same domain or objective.
-
B.
keyOpponents
Indicates that the subject has primary or most significant opponents identified by the object.
-
C.
opponentSupporters
Indicates that the related entities are supporters or backers of opposing sides in a contest, conflict, or competition.
-
D.
enemySpecies
chosen
Indicates that two species are in an antagonistic or hostile relationship, typically viewing each other as enemies.
-
E.
featuresOpponentType
Indicates that an entity involves, includes, or is associated with an opponent of a specified type within a competitive or adversarial context.
- 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_69c68852a9a0819097797e31d492e273 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6dacf8c8c8190a25dbacebeb4b66e |
completed | March 27, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_69c6d7bf0a7c8190b5ed4aca22ba9b97 |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:29 p.m.