Triple
T21736031
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ann Harlan |
E536524
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Kevin Harlan |
—
|
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: Kevin Harlan | Statement: [Ann Harlan, spouse, Kevin Harlan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kevin Harlan Context triple: [Ann Harlan, spouse, Kevin Harlan]
-
A.
Kevin Harlan
chosen
Kevin Harlan is an American sportscaster best known for his energetic play-by-play commentary on NBA and NFL broadcasts.
-
B.
Paul Stine
Paul Stine was a San Francisco cab driver whose 1969 murder is widely believed to be one of the confirmed killings attributed to the Zodiac Killer.
-
C.
John Diehl
John Diehl is an American character actor best known for his role as Detective Larry Zito on the 1980s television series "Miami Vice."
-
D.
John A. Keel
John A. Keel was an American journalist and influential ufologist best known for his investigations into paranormal phenomena and for writing the book that inspired the film "The Mothman Prophecies."
-
E.
Michael Blodgett
Michael Blodgett was an American actor, screenwriter, and producer known for his work in film and television from the late 1960s onward.
- 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_69e0c46df5448190b4322127ffc4c690 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69effd0c0a088190bd1926fa4b73d8f4 |
completed | April 28, 2026, 12:19 a.m. |
Created at: April 16, 2026, 6:49 p.m.