Triple
T37513559
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Act III |
E932573
|
entity |
| Predicate | containsEnemyFaction |
P53524
|
FINISHED |
| Object | Zakarum |
E932580
|
NE 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: Zakarum | Statement: [Act III, containsEnemyFaction, Zakarum]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsEnemyFaction Context triple: [Act III, containsEnemyFaction, Zakarum]
-
A.
hasOpposingFaction
chosen
Indicates that one faction stands in opposition or conflict to another faction.
-
B.
hasEnemiesTrait
Indicates that an entity possesses a characteristic or quality specifically related to having enemies.
-
C.
hasEnemies
Indicates that one entity is in an antagonistic or hostile relationship with another, considering them an enemy.
-
D.
hasOpposingForceType
Indicates that one force is characterized as being of a type that opposes or counteracts another force.
-
E.
hasFriendEnemyRelationshipWith
Indicates a relationship where two entities are simultaneously connected as both friends and enemies, reflecting a mixed or ambivalent association between them.
- F. None of above.
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_69f76ec730988190b5aa4f9cb9afd518 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a01ade363088190b3a3e3dedabd1aa2 |
completed | May 11, 2026, 10:22 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a409538cc1481908c47fbc09e39b11f |
completed | June 28, 2026, 3:30 a.m. |
| PD | Predicate disambiguation | batch_6a01acf3c5788190932bd8fcf27c123d |
completed | May 11, 2026, 10:18 a.m. |
Created at: May 3, 2026, 4:17 p.m.