Triple
T10465639
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Green Man |
E246786
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Steve Power |
E699202
|
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: Steve Power | Statement: [Green Man, producer, Steve Power]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Steve Power Context triple: [Green Man, producer, Steve Power]
-
A.
Steve Power
chosen
Steve Power is a British record producer best known for his work with major pop and rock artists, including producing albums for Robbie Williams.
-
B.
Joe Power
Joe Power is a British psychic medium and author known for his public demonstrations of alleged communication with the dead and related media appearances.
-
C.
Keith Powers
Keith Powers is an American actor known for his roles in films and television series such as "The Tomorrow War," "Straight Outta Compton," and "The New Edition Story."
-
D.
Bryan Power
Bryan Power is an individual whose name is an alternative spelling variant of Brian Power.
-
E.
Keith Powell
Keith Powell is an American actor best known for playing the role of James "Toofer" Spurlock on the television sitcom 30 Rock.
- 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_69d381c16c248190a2fe5b471e584e9c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d5092d6d408190b6bda4d7ced4601e |
completed | April 7, 2026, 1:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d89fe6129881908c658ff977e68135 |
completed | April 10, 2026, 6:59 a.m. |
Created at: April 6, 2026, 12:19 p.m.