Triple
T21481203
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Selleck |
E529996
|
entity |
| Predicate | characterRole |
P268
|
FINISHED |
| Object | Frank Reagan |
—
|
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: Frank Reagan | Statement: [Tom Selleck, characterRole, Frank Reagan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frank Reagan Context triple: [Tom Selleck, characterRole, Frank Reagan]
-
A.
Frank Reagan
chosen
Frank Reagan is the principled New York City Police Commissioner and patriarch of the Reagan family in the television drama "Blue Bloods."
-
B.
Ron Reagan
Ron Reagan is an American political commentator, radio host, and the son of former U.S. President Ronald Reagan.
-
C.
Jack Reagan
Jack Reagan was the father of U.S. President Ronald Reagan and worked as a traveling shoe salesman in the American Midwest.
-
D.
John Neil Reagan
John Neil Reagan was an American radio station manager and advertising executive best known as the older brother of U.S. President Ronald Reagan.
-
E.
John Henninger Reagan
John Henninger Reagan was a prominent 19th-century American politician from Texas who served as a Confederate postmaster general and later as a U.S. congressman and senator.
- 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_69e0c45acc3881908e38d3f28964152b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea338f988190a3044f8d02a567fe |
completed | April 23, 2026, 9:45 a.m. |
Created at: April 16, 2026, 6:21 p.m.