Triple
T4750806
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Skyscraper (2018 film) |
E105471
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object | Michael Sale |
E272646
|
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 Sale | Statement: [Skyscraper (2018 film), editedBy, Michael Sale]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Sale Context triple: [Skyscraper (2018 film), editedBy, Michael Sale]
-
A.
Michael L. Sale
chosen
Michael L. Sale is a film editor known for his work on major Hollywood comedies, including the hit movie "Bridesmaids."
-
B.
Phil Sellers
Phil Sellers was a standout forward for Rutgers University in the 1970s who became the program’s all-time leading scorer and led the team to the 1976 Final Four.
-
C.
Christopher Allen Sale
Christopher Allen Sale is an American professional baseball pitcher known for his dominant left-handed pitching and multiple MLB All-Star selections.
-
D.
Robin Sales
Robin Sales is an editor known for working on the film "Wild Target."
-
E.
Michael Leeson
Michael Leeson was an American television writer and producer best known for co-creating the groundbreaking sitcom "The Cosby Show."
- 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_69bd43f07fa48190954317d01600994a |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd64c83af48190bd57be79c1505e9d |
completed | March 20, 2026, 3:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be43b24440819081f3932eb6b68b48 |
completed | March 21, 2026, 7:07 a.m. |
Created at: March 20, 2026, 1:20 p.m.