Triple
T13172768
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Durkan |
E313018
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | David Durkan |
E313018
|
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: David Durkan | Statement: [David Durkan, name, David Durkan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Durkan Context triple: [David Durkan, name, David Durkan]
-
A.
David Durkan
chosen
David Durkan is a person notable enough to be recognized as a bearer of the surname Durkan, though specific widely known public details about him are not clearly established.
-
B.
James Durkan
James Durkan is a notable individual recognized as a prominent bearer of the Durkan surname.
-
C.
Kevin Durkan
Kevin Durkan is a notable individual recognized for achievements significant enough to be associated with the surname Durkan.
-
D.
Michael Durkan
Michael Durkan is a notable individual who shares the Durkan surname, recognized as a distinguished bearer of that family name.
-
E.
Peter Durkan
Peter Durkan is a notable individual associated with the Durkan name, recognized for his public prominence or professional achievements.
- 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_69d806ac3ee081909b2fd27d060aa974 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98c2f22b881908a0af3af0a0af971 |
completed | April 10, 2026, 11:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7b8c0b24c819082d0ec947b7d99ea |
completed | May 3, 2026, 9:06 p.m. |
Created at: April 9, 2026, 9:13 p.m.