Triple
T34047149
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Paradise concert hall |
E873114
|
entity |
| Predicate | featuredInFilmDirectedBy |
P68097
|
FINISHED |
| Object | Brian De Palma |
E49589
|
NE 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: Brian De Palma | Statement: [The Paradise concert hall, featuredInFilmDirectedBy, Brian De Palma]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuredInFilmDirectedBy Context triple: [The Paradise concert hall, featuredInFilmDirectedBy, Brian De Palma]
-
A.
portrayedInFilmDirectedBy
Indicates that one entity is portrayed as a character in a film that is directed by another specified entity.
-
B.
featuredInFilmBy
Indicates that an entity is prominently included or showcased within a film that is created, directed, or produced by a specified person or organization.
-
C.
featuredInDirector
chosen
Indicates that an entity appears as a featured element within a director’s work, such as a film, show, or other directed production.
-
D.
appearedInFilmDirectedBy
Indicates that an entity appeared in a film whose director is the specified other entity.
-
E.
directedIn
Indicates that one entity served as the director of another entity, such as a person directing a film, episode, or similar work.
- F. None of above.
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_69f349a3ec2c8190b62da76e54231a0f |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a02f441bd408190923b6b68adee8fde |
completed | May 12, 2026, 9:34 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a36a03ed8808190a493815744137501 |
completed | June 20, 2026, 2:14 p.m. |
| PD | Predicate disambiguation | batch_6a02f3c1e64881908569423c9f298f26 |
completed | May 12, 2026, 9:32 a.m. |
Created at: May 1, 2026, 1:51 a.m.