Triple
T6547009
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tommy Harmon |
E151034
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Kelly Harmon |
E288047
|
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: Kelly Harmon | Statement: [Tommy Harmon, child, Kelly Harmon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kelly Harmon Context triple: [Tommy Harmon, child, Kelly Harmon]
-
A.
Kelly Harmon
chosen
Kelly Harmon is an American actress and model known for her television commercials and appearances in series during the 1970s and 1980s.
-
B.
Kelly Grayson
Kelly Grayson is a central character on the science fiction comedy series "The Orville," serving as the ship's first officer and the ex-wife of Captain Ed Mercer.
-
C.
Grace Calhoun
Grace Calhoun is a collegiate athletics administrator known for leading major university sports programs, including serving as athletic director for Brown University's Brown Bears.
-
D.
Rebecca Calhoun
Rebecca Calhoun was the wife of American Revolutionary War general and South Carolina politician Andrew Pickens.
-
E.
Lindy Robbins
Lindy Robbins is an American songwriter known for crafting hit pop songs for major artists across the contemporary music industry.
- 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_69c687f3fd60819083bfa583e5bcfa71 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6adf00aa48190a86a9ad4795363d9 |
completed | March 27, 2026, 4:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6f784b8288190bf3778721fad4eb1 |
completed | March 27, 2026, 9:32 p.m. |
Created at: March 27, 2026, 1:50 p.m.