Triple
T20559201
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Natalie Perwin |
E504799
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Dan Ireland |
—
|
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: Dan Ireland | Statement: [Natalie Perwin, spouse, Dan Ireland]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dan Ireland Context triple: [Natalie Perwin, spouse, Dan Ireland]
-
A.
Dan Ireland
chosen
Dan Ireland was a Canadian-American film director and producer best known as the co-founder and former director of the Seattle International Film Festival.
-
B.
Anthony Ireland
Anthony Ireland was a British actor known for his work in mid-20th-century film and theatre.
-
C.
Dan Healy
Dan Healy is an American audio engineer and producer best known for his long association with the Grateful Dead, helping shape their distinctive live and studio sound.
-
D.
Dan Kavanagh
Dan Kavanagh is the crime-fiction pseudonym used by British novelist Julian Barnes for a series of detective novels.
-
E.
Doug Heffernan
Doug Heffernan is the lovable, blue-collar delivery driver and central character from the sitcom "The King of Queens," known for his humorous misadventures and everyday married life in Queens, New York.
- 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_69e0b4b6587c8190aee63dc7cff244ea |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a5e178648190910795bae5422e50 |
completed | April 20, 2026, 10:17 p.m. |
Created at: April 16, 2026, 11:38 a.m.