Triple
T14982332
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steve Freeling |
E373608
|
entity |
| Predicate | createdBy |
P806
|
FINISHED |
| Object | Michael Grais |
E349956
|
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: Michael Grais | Statement: [Steve Freeling, createdBy, Michael Grais]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Grais Context triple: [Steve Freeling, createdBy, Michael Grais]
-
A.
Michael Grais
chosen
Michael Grais is an American screenwriter and producer best known for co-writing the classic 1982 horror film "Poltergeist."
-
B.
Dr. Jeffrey Squires
Dr. Jeffrey Squires is a disillusioned, pot-smoking psychiatrist who forms an unlikely friendship with a teenage drug dealer in the coming-of-age film "The Wackness."
-
C.
Michael Tadross
Michael Tadross is an American film producer known for working on major Hollywood productions, including big-budget action and fantasy films.
-
D.
Robert Weil
Robert Weil is a name shared by several notable individuals, including figures in fields such as winemaking, philanthropy, and academia.
-
E.
John Weitz
John Weitz was a German-born American fashion designer and author known for his influential menswear designs and historical writings.
- 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_69d85ccbbcd48190acb56e7cf104d8ad |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded6fe42a081909308f788fdf024d5 |
completed | April 15, 2026, 12:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe8bef015c8190bdfb1b9144b2a55c |
completed | May 9, 2026, 1:20 a.m. |
Created at: April 10, 2026, 2:52 a.m.