Triple
T17597404
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pól Brennan |
E428608
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Pádraig Duggan |
—
|
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: Pádraig Duggan | Statement: [Pól Brennan, sibling, Pádraig Duggan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pádraig Duggan Context triple: [Pól Brennan, sibling, Pádraig Duggan]
-
A.
Eamonn Duggan
Eamonn Duggan was an Irish nationalist politician and lawyer who played a key role in the struggle for independence and early Free State politics, including participation in the negotiations that shaped modern Ireland.
-
B.
Patrick Duggan
chosen
Patrick Duggan is a personal name shared by multiple individuals, including figures in fields such as the arts, religion, and public service.
-
C.
Donal McLaughlin
Donal McLaughlin was an American architect and industrial designer best known for creating the iconic emblem of the United Nations.
-
D.
William Duggan
William Duggan is a scholar and author known for his work on strategic intuition and decision-making, particularly in business and leadership contexts.
-
E.
Seamus Deasy
Seamus Deasy is an Irish cinematographer known for his work on feature films and television, including the drama "Queen and Country."
- 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_69d889e1030481909950e140c63255b9 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e469ecfb108190a9e7a5b380f8ab93 |
completed | April 19, 2026, 5:36 a.m. |
Created at: April 10, 2026, 5:51 a.m.