Triple
T21762363
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Schwarz |
E537193
|
entity |
| Predicate | collaboratedWith |
P435
|
FINISHED |
| Object | Michael Green |
—
|
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: Michael Green | Statement: [Schwarz, collaboratedWith, Michael Green]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Green Context triple: [Schwarz, collaboratedWith, Michael Green]
-
A.
Michael Green
Michael Green is a fictional character from the 1994 romantic drama film "When a Man Loves a Woman," which explores the impact of alcoholism on a marriage and family.
-
B.
Michael Green
chosen
Michael Green is a prominent British theoretical physicist known for his pioneering work in string theory and quantum gravity.
-
C.
Michael Green
Michael Green is an American screenwriter and producer known for his work on major films and television series, including projects like "Logan," "Blade Runner 2049," and "American Gods."
-
D.
Michael Greene
Michael Greene is an actor best known for his role in the 1985 comedy film "Lost in America."
-
E.
Jeffrey Harvey
Jeffrey Harvey is a theoretical physicist known for his pioneering contributions to string theory, including foundational work on heterotic string models.
- 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_69e0c46f5d1c8190bf830409e98464e5 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f01d9369f88190b4be11b82fe75a17 |
completed | April 28, 2026, 2:38 a.m. |
Created at: April 16, 2026, 6:51 p.m.