Triple
T28136538
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oliver Twist (1948 film) |
E714220
|
entity |
| Predicate | characterPortrayedByRobertNewton |
P184845
|
FINISHED |
| Object | Bill Sikes |
—
|
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: Bill Sikes | Statement: [Oliver Twist (1948 film), characterPortrayedByRobertNewton, Bill Sikes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: characterPortrayedByRobertNewton Context triple: [Oliver Twist (1948 film), characterPortrayedByRobertNewton, Bill Sikes]
-
A.
characterPortrayedByRodTaylor
Indicates that a given character is portrayed or played by the actor Rod Taylor.
-
B.
characterPlayedByRobertPatrick
Indicates that a given character is portrayed or acted by Robert Patrick.
-
C.
characterPlayedByRichardHarris
Indicates that the subject is a character that was portrayed by the actor Richard Harris.
-
D.
DavidNivenRole
Indicates that a person played a specific role or character in a work associated with David Niven (e.g., a film, TV show, or stage production).
-
E.
characterVoicedBy_James Brolin
Indicates that a character is voiced by James Brolin in a performance or production.
- 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_69efd6af156c81908f50c2cd7db0e1ef |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f7b628b17c8190aa058c1a51852a27 |
completed | May 3, 2026, 8:55 p.m. |
| PD | Predicate disambiguation | batch_69f7b4c06f5881908f0b98cad6796478 |
completed | May 3, 2026, 8:49 p.m. |
| PDg | Predicate description generation | batch_69f7b5cadd308190a864245a21b08f9a |
completed | May 3, 2026, 8:53 p.m. |
Created at: April 27, 2026, 9:50 p.m.