Triple
T38604857
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Five (Zombies map) |
E934313
|
entity |
| Predicate | hasUniqueEnemy |
P195120
|
FINISHED |
| Object | Pentagon Thief |
—
|
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: Pentagon Thief | Statement: [Five (Zombies map), hasUniqueEnemy, Pentagon Thief]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasUniqueEnemy Context triple: [Five (Zombies map), hasUniqueEnemy, Pentagon Thief]
-
A.
hasEnemyLeader
Indicates that one entity is the primary opposing or adversarial leader in relation to another entity.
-
B.
hasCommonEnemies
Indicates that two or more entities share at least one enemy in common.
-
C.
hasOpposingForceType
Indicates that one force is characterized as being of a type that opposes or counteracts another force.
-
D.
hasEnemyOccupationContext
Indicates a contextual relationship in which an entity is subject to, or characterized by, control or occupation by an enemy force.
-
E.
hasOpposingSide
Indicates that one entity possesses or is associated with another entity that lies on the opposite or facing side relative to a reference orientation or boundary.
- F. None of above. chosen
Provenance (4 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_69f76ecc17688190b389b693a5927501 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fda5003cdc8190a558501271389912 |
completed | May 8, 2026, 8:55 a.m. |
| PD | Predicate disambiguation | batch_69fda05bfc2c819096821a5300e9bb24 |
completed | May 8, 2026, 8:35 a.m. |
| PDg | Predicate description generation | batch_69fda4fe67a08190bdaa84ceabd6de6c |
completed | May 8, 2026, 8:55 a.m. |
Created at: May 3, 2026, 4:32 p.m.