Triple
T29050670
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Edward Norton as Bruce Banner / Hulk |
E735255
|
entity |
| Predicate | recastEffectiveFromFilm |
P165960
|
FINISHED |
| Object | The Avengers (2012 film) |
—
|
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 Avengers (2012 film) | Statement: [Edward Norton as Bruce Banner / Hulk, recastEffectiveFromFilm, The Avengers (2012 film)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recastEffectiveFromFilm Context triple: [Edward Norton as Bruce Banner / Hulk, recastEffectiveFromFilm, The Avengers (2012 film)]
-
A.
releasedWithFilm
Indicates that one work (such as a soundtrack, game, or related media) was issued or made available at the same time as a particular film.
-
B.
recastInYear
Indicates that an existing work, role, or production was cast again with different performers in a specified year.
-
C.
recastOf
Indicates that one entity is a new or different version, adaptation, or reinterpretation of another, typically replacing or redoing the original in a similar role or context.
-
D.
remakeReleaseYear
Indicates the year in which a remake of an original work was released.
-
E.
settingTimeRelativeToFilms
Indicates the temporal relationship of one film’s setting relative to the settings of other films (e.g., earlier, later, or at the same time).
- F. None of above. chosen
Provenance (4 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_69f077e64b88819094d37bdbca8191b3 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f66065c17081908a0bb6b8a7f16558 |
completed | May 2, 2026, 8:36 p.m. |
| PD | Predicate disambiguation | batch_69f659d297cc8190b2b962ba30a1edb3 |
completed | May 2, 2026, 8:08 p.m. |
| PDg | Predicate description generation | batch_69f65ad638ac8190a17bb987fce53279 |
completed | May 2, 2026, 8:13 p.m. |
Created at: April 28, 2026, 10:08 a.m.