Triple
T20174256
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hayley Vaughan |
E492047
|
entity |
| Predicate | father |
P120
|
FINISHED |
| Object | Adam Chandler |
—
|
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: Adam Chandler | Statement: [Hayley Vaughan, father, Adam Chandler]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adam Chandler Context triple: [Hayley Vaughan, father, Adam Chandler]
-
A.
Adam Chandler
chosen
Adam Chandler is a wealthy, manipulative business tycoon and longtime central villain-antihero on the soap opera *All My Children*.
-
B.
Mike Sekowsky
Mike Sekowsky was an American comic book artist best known for his influential work at DC Comics, including early Justice League of America stories.
-
C.
Joe Nuxhall
Joe Nuxhall was an American left-handed pitcher and longtime Cincinnati Reds broadcaster, famously known as the youngest player in modern Major League Baseball history.
-
D.
Mike Roark
Mike Roark is the fictional head of Los Angeles' Office of Emergency Management who leads the effort to combat a sudden volcanic eruption in the disaster film "Volcano" (1997).
-
E.
Todd Casey
Todd Casey is a screenwriter best known for co-writing the 2015 horror-comedy film "Krampus."
- 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_69da6266c6888190bc1a3ecf24814d34 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e6684a33688190b22cfc16907e76bc |
completed | April 20, 2026, 5:54 p.m. |
Created at: April 11, 2026, 11:36 p.m.