Triple
T12148834
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Game of Death |
E289399
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Robert Wall |
E270133
|
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: Robert Wall | Statement: [Game of Death, starring, Robert Wall]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Robert Wall Context triple: [Game of Death, starring, Robert Wall]
-
A.
Robert Wall
chosen
Robert Wall is a British actor and martial artist best known for appearing in several Bruce Lee films, including "Enter the Dragon" and "Way of the Dragon."
-
B.
Eric Waller
Eric Waller is an entrepreneur best known as a co-founder of the mobile-focused ticketing platform SeatGeek.
-
C.
Michael Wallis
Michael Wallis is an American historian and author best known for his works on Route 66 and the American West, as well as for voicing the Sheriff in Pixar’s Cars films.
-
D.
Michael Wall
Michael Wall is a biotechnology entrepreneur best known as the founder of the biopharmaceutical company Alkermes.
-
E.
Robert Walls
Robert Walls is a former Australian rules football player and premiership-winning coach best known for his coaching stints with several VFL/AFL clubs, including the Brisbane Bears.
- 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_69d6ab4c6710819097a9d228382dde43 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d915ad6ef08190b334a97d6ab41487 |
completed | April 10, 2026, 3:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f5f698c5648190a5a29e08f2b7d8ab |
completed | May 2, 2026, 1:05 p.m. |
Created at: April 8, 2026, 9:49 p.m.