Triple
T31657668
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Low Shoulder |
E807900
|
entity |
| Predicate | publicImageInFilm |
P177716
|
FINISHED |
| Object | heroic band that survived a tragedy |
—
|
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: heroic band that survived a tragedy | Statement: [Low Shoulder, publicImageInFilm, heroic band that survived a tragedy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: publicImageInFilm Context triple: [Low Shoulder, publicImageInFilm, heroic band that survived a tragedy]
-
A.
placementInFilm
Indicates the specific position or occurrence of something within the sequence or structure of a film.
-
B.
filmPortrayer
Indicates that one entity portrays or plays the role of another entity (such as a character or person) in a film.
-
C.
basedOnInFilm
Indicates that a film is derived from, adapted from, or otherwise uses as its source material another work, event, or concept.
-
D.
isPortrayedIn
chosen
Indicates that an entity is depicted or represented within a particular work, medium, or portrayal.
-
E.
isFromFilm
Indicates that something (such as a quote, character, scene, or element) originates from or appears in a particular film.
- 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_69f348daf95c81908b4c985b7ddcd0b3 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69fe7bfc94bc81909eeec946e8c1c450 |
completed | May 9, 2026, 12:12 a.m. |
| PD | Predicate disambiguation | batch_69fe7b74a1188190886f128e07f712da |
completed | May 9, 2026, 12:10 a.m. |
Created at: April 30, 2026, 10:56 p.m.