Triple
T26308265
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | My Hero |
E661745
|
entity |
| Predicate | protagonistCoverOccupation |
P21567
|
FINISHED |
| Object | health food shop owner |
—
|
LITERAL 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: health food shop owner | Statement: [My Hero, protagonistCoverOccupation, health food shop owner]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: protagonistCoverOccupation Context triple: [My Hero, protagonistCoverOccupation, health food shop owner]
-
A.
otherProtagonistOccupation
Indicates that another main character in the narrative has a specific occupation or job role.
-
B.
featuresProtagonistOccupation
chosen
Indicates that the work’s main character has a specified occupation or job role.
-
C.
protagonistSocialStatus
Indicates the social standing or class position held by the story’s main character in relation to others in their society.
-
D.
protagonistDescription
Indicates that a text provides a descriptive summary or characterization of the story’s main protagonist.
-
E.
portrayedProfessionOfCharacter
Indicates that one entity is the profession or occupation depicted as being held by a particular character.
- 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_69ee812dacfc81908484aade9120fba9 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f60ee46ed08190bfba31e879318fea |
completed | May 2, 2026, 2:49 p.m. |
| PD | Predicate disambiguation | batch_69f60b874cc88190a487230abb69efea |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 26, 2026, 10:20 p.m.