Triple
T29150598
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sheriff Graham Humbert |
E738895
|
entity |
| Predicate | fairyTaleIdentity |
P131560
|
FINISHED |
| Object | The Huntsman |
—
|
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: The Huntsman | Statement: [Sheriff Graham Humbert, fairyTaleIdentity, The Huntsman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fairyTaleIdentity Context triple: [Sheriff Graham Humbert, fairyTaleIdentity, The Huntsman]
-
A.
folkloreCharacter
chosen
Indicates that one entity is a character originating from the traditional stories, myths, or legends associated with the other entity.
-
B.
hasFairyCharacters
Indicates that the subject includes or features characters that are fairies.
-
C.
fandomIdentity
Indicates that an entity identifies as a fan or member of a particular fandom associated with another entity.
-
D.
identityNarrative
Indicates a relationship where an entity’s sense of self or identity is constructed, expressed, or shaped through a narrative or story.
-
E.
roleInTangled
Indicates that an entity has a specific role or function within the context of "Tangled" (e.g., the film, story, or related production).
- 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_69f07cb46f148190874eb8576a447567 |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f662a5297881909fe6bc9b5a013df3 |
completed | May 2, 2026, 8:46 p.m. |
| PD | Predicate disambiguation | batch_69f65c2376a08190be5215171e908e69 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 11:42 a.m.