Triple
T21686305
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Patrick Sarsfield |
E535237
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Sarsfield |
—
|
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: Sarsfield | Statement: [Patrick Sarsfield, familyName, Sarsfield]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sarsfield Context triple: [Patrick Sarsfield, familyName, Sarsfield]
-
A.
Sarsfield
Sarsfield is a small rural community located within Russell County in Ontario, Canada.
-
B.
Sarsfield
chosen
Sarsfield is an Irish surname most famously associated with Patrick Sarsfield, a Jacobite military leader during the Williamite War in Ireland.
-
C.
Stradbally
Stradbally is a small Irish town in County Laois, best known for hosting the annual Electric Picnic music and arts festival.
-
D.
Ballsbridge
Ballsbridge is an affluent, largely residential district in Dublin, Ireland, known for its embassies, upscale homes, and proximity to the city center.
-
E.
Donnycarney
Donnycarney is a residential suburb on the north side of Dublin, Ireland, known for its strong local community and proximity to the city centre.
- 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_69e0c469b6ec8190aee4cadd1527db91 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef96cb69f081908ed0c7ebea429898 |
completed | April 27, 2026, 5:03 p.m. |
Created at: April 16, 2026, 6:44 p.m.