Triple
T15541859
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Broyles Jr. |
E370498
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | David Broyles |
E370498
|
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: David Broyles | Statement: [William Broyles Jr., child, David Broyles]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Broyles Context triple: [William Broyles Jr., child, David Broyles]
-
A.
David Broyles
chosen
David Broyles is one of the children of American screenwriter and Vietnam War veteran William Broyles Jr.
-
B.
John Ketcham
John Ketcham is a film producer best known for his work on the biographical sports drama "The Hurricane."
-
C.
Jerry Warriner
Jerry Warriner is the charming, witty husband whose marital misadventures and romantic sparring drive the screwball comedy of the classic film "The Awful Truth."
-
D.
Tom B. Brown
Tom B. Brown is a machine learning researcher known for leading work on large-scale language models, including the influential GPT-3 paper "Language Models are Few-Shot Learners."
-
E.
Richard Stolley
Richard Stolley was an influential American magazine editor best known for shaping modern celebrity journalism as the founding managing editor of People magazine.
- 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_69d85cc521a08190921fb50319dddc34 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04432c3808190bb5b653bf8de30c6 |
completed | April 16, 2026, 2:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff56bdbca08190b5eb541c5eb4bb09 |
completed | May 9, 2026, 3:46 p.m. |
Created at: April 10, 2026, 4:07 a.m.