Triple
T21311475
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Sacks |
E525347
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Michael Sacks |
—
|
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 Sacks | Statement: [Michael Sacks, name, Michael Sacks]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Sacks Context triple: [Michael Sacks, name, Michael Sacks]
-
A.
Michael Sacks
chosen
Michael Sacks is an American actor best known for his role as Billy Pilgrim in the film adaptation of Kurt Vonnegut’s "Slaughterhouse-Five."
-
B.
Michael Saks
Michael Saks is an American mathematician and theoretical computer scientist known for his contributions to combinatorics, complexity theory, and related areas.
-
C.
Martin Sacks
Martin Sacks is an Australian actor best known for his long-running role as Detective P.J. Hasham on the television drama series "Blue Heelers."
-
D.
Greg Sacks
Greg Sacks is an American former NASCAR driver best known for his surprise victory in the 1985 Firecracker 400 and for competing part-time in the Cup Series through the 1980s and 1990s.
-
E.
Michael D. Rosenthal
Michael D. Rosenthal is a writer best known as the author whose work inspired the "Twilight Zone" episode "A Kind of Stopwatch."
- 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_69e0b518b8948190ad69cf9a8784d397 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e75dc926c881909d70a317070ef295 |
completed | April 21, 2026, 11:21 a.m. |
Created at: April 16, 2026, 4:17 p.m.