Triple
T33854377
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gary Oldman as Norman Stansfield |
E867729
|
entity |
| Predicate | interactsWithCharacters |
P84701
|
FINISHED |
| Object | Léon |
—
|
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: Léon | Statement: [Gary Oldman as Norman Stansfield, interactsWithCharacters, Léon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: interactsWithCharacters Context triple: [Gary Oldman as Norman Stansfield, interactsWithCharacters, Léon]
-
A.
collaboratesWithCharacter
Indicates that one character works together with another character toward a shared goal or activity.
-
B.
meetsFictionalCharacter
Indicates that one entity encounters or comes into contact with a fictional character.
-
C.
heroInteraction
Indicates an interaction or engagement occurring between a hero and another entity, such as assisting, confronting, or collaborating.
-
D.
encountersCharacter
chosen
Indicates that one character comes into contact with or meets another character, typically within a particular situation or context.
-
E.
characterDuet
Indicates a relationship where two characters perform together as a duet in a shared scene, song, or action.
- 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_69f349943ccc8190a3c41a3e0ae46cbf |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fdd5fba5048190b7d430ae2054a1fd |
completed | May 8, 2026, 12:24 p.m. |
| PD | Predicate disambiguation | batch_69fdd35f76f88190a1854ea27132f9c7 |
completed | May 8, 2026, 12:13 p.m. |
Created at: May 1, 2026, 1:47 a.m.