Triple
T6018121
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Christopher Heaney |
E133996
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Michael Heaney |
E132201
|
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: Michael Heaney | Statement: [Christopher Heaney, sibling, Michael Heaney]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Heaney Context triple: [Christopher Heaney, sibling, Michael Heaney]
-
A.
Michael Heaney
chosen
Michael Heaney is the son of Nobel Prize–winning Irish poet Seamus Heaney and is known for his work as a librarian and bibliographer.
-
B.
Christopher Heaney
Christopher Heaney is one of the children of Nobel Prize–winning Irish poet Seamus Heaney.
-
C.
Paul Laverty
Paul Laverty is a Scottish screenwriter best known for his long-standing collaboration with director Ken Loach on socially and politically charged films.
-
D.
Michael McElroy
Michael McElroy is an American actor and Tony-nominated Broadway performer known for his work in musical theatre and film.
-
E.
John Callaghan
John Callaghan is a relatively obscure individual whose name is notably recorded as a bearer of the surname Callaghan.
- 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_69c008742a5c8190b9cb9c2787a3d8b3 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04f8589d0819089ae7840461640f6 |
completed | March 22, 2026, 8:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c108b842c48190b9469e2892a213d3 |
completed | March 23, 2026, 9:32 a.m. |
Created at: March 22, 2026, 4:07 p.m.