Triple
T13012187
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Douglas Slocombe |
E322443
|
entity |
| Predicate | workedOn |
P3
|
FINISHED |
| Object | Rollerball |
E54496
|
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: Rollerball | Statement: [Douglas Slocombe, workedOn, Rollerball]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rollerball Context triple: [Douglas Slocombe, workedOn, Rollerball]
-
A.
Rollerball
chosen
Rollerball is a 1975 dystopian science fiction sports film depicting a violent future game used by corporations to control society.
-
B.
Logan's Run
Logan's Run is a 1976 science fiction film set in a dystopian future where citizens are executed at age 30, following a "Sandman" who begins to question the system.
-
C.
The Running Man
The Running Man is a 1963 British thriller film directed by Carol Reed, centered on an insurance fraud scheme and its tense aftermath.
-
D.
The Running Man
The Running Man is a 1987 dystopian action film starring Arnold Schwarzenegger as a framed cop forced to participate in a deadly televised game show in a totalitarian future.
-
E.
Midnight Runner
Midnight Runner is a fast-paced thriller novel by Jack Higgins that follows covert operatives, international intrigue, and high-stakes action in the author’s signature suspenseful style.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d807657e8c8190bd9435ee2f823845 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d97ecbb8f4819094d55eb07cb5ad97 |
completed | April 10, 2026, 10:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6cbc77f308190b3b47f7a092db434 |
completed | May 3, 2026, 4:15 a.m. |
Created at: April 9, 2026, 8:49 p.m.