Triple
T37457687
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shadowreaper Anduin |
E930839
|
entity |
| Predicate | transformsHero |
P119384
|
FINISHED |
| Object | Anduin Wrynn |
—
|
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: Anduin Wrynn | Statement: [Shadowreaper Anduin, transformsHero, Anduin Wrynn]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transformsHero Context triple: [Shadowreaper Anduin, transformsHero, Anduin Wrynn]
-
A.
treatsFormOfHero
Indicates that one entity administers or applies a particular form or version of a hero (e.g., a drug, remedy, or protective agent) as a treatment to another entity.
-
B.
wasTransformedBy
Indicates that an entity has undergone a change of state, form, or condition as the result of an action, process, or agent.
-
C.
transformsCharacterInto
chosen
Indicates that one entity causes or undergoes a change that turns a character into another form, state, or identity.
-
D.
targetsHeroes
Indicates that an entity directs attacks, actions, or effects specifically toward hero characters.
-
E.
heroPower
Indicates that an entity possesses or is associated with a particular heroic power or special ability.
- 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_69f76ec1a1148190b0a961f188d621b0 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ffbb1c5bf88190a0bf791213045885 |
completed | May 9, 2026, 10:54 p.m. |
| PD | Predicate disambiguation | batch_69ffba0ab0f881908f84ef81f7a1bfe8 |
completed | May 9, 2026, 10:49 p.m. |
Created at: May 3, 2026, 4:17 p.m.