Triple
T37125596
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ricou Browning |
E919381
|
entity |
| Predicate | performedUnderwaterScenesIn |
P74071
|
FINISHED |
| Object | Creature from the Black Lagoon |
—
|
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: Creature from the Black Lagoon | Statement: [Ricou Browning, performedUnderwaterScenesIn, Creature from the Black Lagoon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: performedUnderwaterScenesIn Context triple: [Ricou Browning, performedUnderwaterScenesIn, Creature from the Black Lagoon]
-
A.
sinkingRecordedOnFilm
Indicates that the act or process of sinking was captured or documented on film.
-
B.
actsIn
chosen
Indicates that an entity performs or appears in a creative work, such as a film, play, or show.
-
C.
partOfFilmographyOf
Indicates that a work (such as a film, show, or role) is included in the body of screen-related works credited to a particular person.
-
D.
sungInFilmBy
Indicates that a particular song was vocally performed in a film by a specific person or group.
-
E.
placementInFilm
Indicates the specific position or occurrence of something within the sequence or structure of a 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_69f76e9d13e48190a108f7fbf80ff375 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ff46afe7e481908f2862ed11c88db2 |
completed | May 9, 2026, 2:37 p.m. |
| PD | Predicate disambiguation | batch_69ff45e9151881909c444a655e852165 |
completed | May 9, 2026, 2:34 p.m. |
Created at: May 3, 2026, 4:15 p.m.