Triple
T36060584
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boxer Santaros |
E1043065
|
entity |
| Predicate | inUniverseFilmTitle |
P114505
|
FINISHED |
| Object | The Power |
—
|
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 Power | Statement: [Boxer Santaros, inUniverseFilmTitle, The Power]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inUniverseFilmTitle Context triple: [Boxer Santaros, inUniverseFilmTitle, The Power]
-
A.
inUniverseTitle
Indicates that a work’s title is the one used within the fictional universe itself, as opposed to an external or real-world title.
-
B.
sourceFilmTitle
Indicates the title of the film from which a referenced work, element, or derivative content originates.
-
C.
includedInFilm
Indicates that one entity (such as a scene, segment, or element) is contained within or forms part of a particular film.
-
D.
film6Title
Indicates the title assigned to the sixth film in a sequence or collection.
-
E.
filmWithinFilmTitle
chosen
Indicates that a title refers to a fictional film that appears within another (primary) 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_69f76e2f09448190b0486d5ecad5e243 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fd32848ea88190a71e6df402bbb30e |
completed | May 8, 2026, 12:47 a.m. |
| PD | Predicate disambiguation | batch_69fd2d7e95588190991d5f21e25155df |
completed | May 8, 2026, 12:25 a.m. |
Created at: May 3, 2026, 4:08 p.m.