Triple
T26260180
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roche family |
E656824
|
entity |
| Predicate | hasTraditionalSeat |
P64286
|
FINISHED |
| Object | Fermoy, County Cork |
—
|
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: Fermoy, County Cork | Statement: [Roche family, hasTraditionalSeat, Fermoy, County Cork]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTraditionalSeat Context triple: [Roche family, hasTraditionalSeat, Fermoy, County Cork]
-
A.
hasHistoricalSeat
chosen
Indicates that an entity possesses or is associated with a historically significant seat, location, or place of authority.
-
B.
hasSeatsForConstituency
Indicates that a governing body or institution allocates or provides a certain number of representative seats for a specific constituency.
-
C.
hasFormerSeat
Indicates that an entity previously held a particular seat, position, or place but no longer does so.
-
D.
hasJudicialSeat
Indicates that an entity holds an official position or seat within a judicial body or court.
-
E.
hasPermanentSeats
Indicates that certain entities hold ongoing, non-rotating positions or places within a defined structure or body.
- F. None of above.
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_69ee5b4e21bc819082be98bc9ab09796 |
completed | April 26, 2026, 6:37 p.m. |
| NER | Named-entity recognition | batch_69f7308a096081909d66a56f3c926806 |
completed | May 3, 2026, 11:24 a.m. |
| PD | Predicate disambiguation | batch_69f72a00c5f081908b6539d15baf4e12 |
completed | May 3, 2026, 10:57 a.m. |
Created at: April 26, 2026, 9:10 p.m.