Triple
T15904453
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rick Ducommun |
E385672
|
entity |
| Predicate | hasRelative |
P367
|
FINISHED |
| Object | Peter Ducommun |
E1185409
|
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: Peter Ducommun | Statement: [Rick Ducommun, hasRelative, Peter Ducommun]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Peter Ducommun Context triple: [Rick Ducommun, hasRelative, Peter Ducommun]
-
A.
Richard Ducommun
chosen
Richard Ducommun was a Canadian character actor and comedian known for his supporting roles in films such as "The 'Burbs" and "Groundhog Day."
-
B.
Patrick Meese
Patrick Meese is an American musician best known as a member of the soul and rock band Nathaniel Rateliff & The Night Sweats.
-
C.
Paul J. LeBlanc
Paul J. LeBlanc is an American higher education leader known for transforming Southern New Hampshire University into one of the largest and most innovative online universities in the United States.
-
D.
John Roberdeau
John Roberdeau is a film producer best known for his work on Terrence Malick’s acclaimed war drama "The Thin Red Line."
-
E.
Charles Boustany
Charles Boustany is an American politician and former Republican U.S. Representative from Louisiana.
- 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_69d86da686e4819097cbf3b1fc2d881d |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1563f74d88190a3d92ca0ad46e867 |
completed | April 16, 2026, 9:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffbe6e844481908227ec9e46ac9f4d |
completed | May 9, 2026, 11:08 p.m. |
Created at: April 10, 2026, 4:52 a.m.