Triple
T7044313
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matt Dillon |
E163592
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Kevin Dillon |
E338607
|
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: Kevin Dillon | Statement: [Matt Dillon, sibling, Kevin Dillon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kevin Dillon Context triple: [Matt Dillon, sibling, Kevin Dillon]
-
A.
Kevin Dillon
chosen
Kevin Dillon is an American actor best known for his roles in films like "Platoon" and as Johnny "Drama" Chase on the television series "Entourage."
-
B.
Tim Healy
Tim Healy is an English actor best known for his comedic and dramatic television roles, particularly in popular British series.
-
C.
Tim Healy
Tim Healy was an Irish nationalist politician, lawyer, and writer who became the first Governor-General of the Irish Free State.
-
D.
Michael Cerveris
Michael Cerveris is a Tony Award–winning American actor and singer known for his work on Broadway and in film and television.
-
E.
Joel Murray
Joel Murray is an American actor and comedian known for his character roles in film and television, as well as for his voice work in animated 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_69c6885f598c8190b6b6495c59d8d962 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e23730888190a827ca5c61c4eed0 |
completed | March 27, 2026, 8:01 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7887799f48190b4fa311defd8e9fd |
completed | March 28, 2026, 7:51 a.m. |
Created at: March 27, 2026, 2:37 p.m.