Triple
T38588340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Banshee Queen |
E932395
|
entity |
| Predicate | brokeFreeFrom |
P73865
|
FINISHED |
| Object | Lich King |
—
|
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: Lich King | Statement: [Banshee Queen, brokeFreeFrom, Lich King]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: brokeFreeFrom Context triple: [Banshee Queen, brokeFreeFrom, Lich King]
-
A.
willBreakFreeDuring
Indicates that an entity is expected to escape or become free from another entity or constraint during a specified time or event.
-
B.
freeFrom
chosen
Indicates that one entity does not contain, is not affected by, or is exempt from another specified entity, condition, or constraint.
-
C.
releaseFrom
Indicates that one entity causes or authorizes another entity to be freed, discharged, or removed from a prior state of confinement, obligation, or restriction.
-
D.
brokenBy
Indicates that one entity causes the damage, destruction, or loss of functionality of another entity.
-
E.
freedFromCorruptionBy
Indicates that an entity was previously corrupted or tainted and was restored or purified through the actions or influence of another entity.
- 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_69f76ec654d48190b421111cf26e54d9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcdaa36f90819093f8661969990c7d |
completed | May 7, 2026, 6:32 p.m. |
| PD | Predicate disambiguation | batch_69fcd8fefc588190b063d7ea1ec87b07 |
completed | May 7, 2026, 6:25 p.m. |
Created at: May 3, 2026, 4:32 p.m.