Triple
T17030881
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Woodrow Tracy Harrelson |
E413189
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Harrelson |
E413190
|
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: Harrelson | Statement: [Woodrow Tracy Harrelson, familyName, Harrelson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harrelson Context triple: [Woodrow Tracy Harrelson, familyName, Harrelson]
-
A.
Harrelson
chosen
Harrelson is the surname of American actor Woody Harrelson, known for his versatile roles in film and television.
-
B.
Derrel McKinley Harrelson
Derrel McKinley "Bud" Harrelson was an American Major League Baseball shortstop and coach, best known for his long tenure with the New York Mets and his strong defensive play.
-
C.
Morry Hollowell
Morry Hollowell is a comic book colorist best known for his work on major Marvel titles, including the "Civil War" crossover event.
-
D.
Harold Hogan
Harold "Happy" Hogan is a fictional character in Marvel Comics and the Marvel Cinematic Universe, best known as Tony Stark’s loyal friend, bodyguard, and later head of security.
-
E.
Sam Hamm
Sam Hamm is an American screenwriter best known for co-writing Tim Burton’s 1989 film "Batman" and contributing to other comic book–related projects.
- 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_69d886cd18288190b006abab23f811b7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d5d918ec8190b54c40c2a5e9b6b9 |
completed | April 18, 2026, 7:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a011b5748bc8190832737a70219e7a1 |
completed | May 10, 2026, 11:57 p.m. |
Created at: April 10, 2026, 5:33 a.m.