Triple
T278796
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Laurence Olivier |
E5308
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Olivier |
E5308
|
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: Olivier | Statement: [Laurence Olivier, familyName, Olivier]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Olivier Context triple: [Laurence Olivier, familyName, Olivier]
-
A.
Laurence Olivier
chosen
Laurence Olivier was a renowned 20th-century English actor and director, widely regarded as one of the greatest performers in the history of stage and screen.
-
B.
Richard Attenborough
Richard Attenborough was an acclaimed English actor, filmmaker, and producer known for films such as "Gandhi" and "Jurassic Park."
-
C.
Laurence Olivier Award
The Laurence Olivier Award is one of the most prestigious British theatre honors, recognizing outstanding achievements in London’s West End stage productions.
-
D.
Bill Nighy
Bill Nighy is an English actor known for his distinctive voice and acclaimed performances in films such as "Love Actually," "Pirates of the Caribbean," and "About Time."
-
E.
Omar Sharif
Omar Sharif was an acclaimed Egyptian actor known internationally for his roles in classic films such as "Lawrence of Arabia" and "Doctor Zhivago."
- 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_69a257e6c8788190987dfe705ca2912a |
completed | Feb. 28, 2026, 2:50 a.m. |
| NER | Named-entity recognition | batch_69a25dee7830819087f153769a8496b9 |
completed | Feb. 28, 2026, 3:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a39d04650c8190bda8f1b982c645df |
completed | March 1, 2026, 1:57 a.m. |
Created at: Feb. 28, 2026, 2:59 a.m.