Triple
T16018456
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | On Dangerous Ground |
E388530
|
entity |
| Predicate | featuresCharacter |
P626
|
FINISHED |
| Object | Sean Dillon |
—
|
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: Sean Dillon | Statement: [On Dangerous Ground, featuresCharacter, Sean Dillon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sean Dillon Context triple: [On Dangerous Ground, featuresCharacter, Sean Dillon]
-
A.
Sean Dillon
chosen
Sean Dillon is a former IRA enforcer turned covert operative who serves as the central anti-hero in Jack Higgins' popular thriller novel series.
-
B.
Daniel Dillon
Daniel Dillon is a central character in Thomas Hardy’s novel "The Mayor of Casterbridge," known for his complex moral struggles and tragic personal downfall.
-
C.
Alan Dillon
Alan Dillon is an Irish Fine Gael politician and former Gaelic footballer who serves as a Teachta Dála (TD) in the national parliament.
-
D.
Steve Dillon
Steve Dillon was a British comic book artist best known for co-creating and illustrating the acclaimed series "Preacher."
-
E.
Luke Doolan
Luke Doolan is an Australian film editor and filmmaker best known for his work on acclaimed films such as "Animal Kingdom."
- 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_69d86dabcb7c8190b6a39d6831d2fa1b |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e18296a7008190b72ab2ab02d0fbc9 |
completed | April 17, 2026, 12:45 a.m. |
Created at: April 10, 2026, 4:55 a.m.