Triple
T29050850
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bruce Banner |
E735257
|
entity |
| Predicate | portrayedPreviouslyBy |
P52433
|
FINISHED |
| Object | Edward Norton |
—
|
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: Edward Norton | Statement: [Bruce Banner, portrayedPreviouslyBy, Edward Norton]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portrayedPreviouslyBy Context triple: [Bruce Banner, portrayedPreviouslyBy, Edward Norton]
-
A.
previouslyPortrayedBy
chosen
Indicates that the subject entity was portrayed in the past by the specified actor or performer.
-
B.
portrayedBy
Indicates that one entity serves as the actor or performer who represents or plays the role of another entity in a work or medium.
-
C.
alsoPortrayedBy
Indicates that the same role or character is portrayed by an additional, different performer or actor.
-
D.
laterPortrayedAs
Indicates that an entity is subsequently depicted or represented as another character, role, or form in a later work or context.
-
E.
portrayedByInSequel
Indicates that an entity is portrayed by a particular actor or performer specifically in a sequel work (e.g., a sequel film, series, or game).
- 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_69f077e64b88819094d37bdbca8191b3 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69fce7671f108190bf3ebf54339068b5 |
completed | May 7, 2026, 7:26 p.m. |
| PD | Predicate disambiguation | batch_69fce5b5a84c81908ac1b5b9f08d48d0 |
completed | May 7, 2026, 7:19 p.m. |
Created at: April 28, 2026, 10:08 a.m.