Triple
T19545625
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Patrick Magee |
E489039
|
entity |
| Predicate | workedWith |
P398
|
FINISHED |
| Object | Peter Brook |
—
|
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: Peter Brook | Statement: [Patrick Magee, workedWith, Peter Brook]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Peter Brook Context triple: [Patrick Magee, workedWith, Peter Brook]
-
A.
Peter Brook
chosen
Peter Brook was a highly influential British theatre and film director renowned for his innovative, minimalist stagings and groundbreaking work with Shakespeare and experimental theatre.
-
B.
Peter Brooks
Peter Brooks is a relatively obscure individual for whom no widely recognized public information or distinguishing achievements are readily available.
-
C.
Peter Brooks
Peter Brooks was a prominent 19th-century Chicago real estate developer and investor known for financing major commercial buildings, including landmark early skyscrapers.
-
D.
Robert Lepage
Robert Lepage is a renowned Canadian playwright, actor, and director celebrated for his innovative, multimedia-driven approach to theatre and opera.
-
E.
Peter Whitehead
Peter Whitehead is a writer known for his work on the film "Macho Man."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8db5b6c8190984b61f91981f575 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63876bacc8190b17e2087de679785 |
completed | April 20, 2026, 2:30 p.m. |
Created at: April 10, 2026, 1:41 p.m.