Triple
T27126120
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mayor of Derry |
E681436
|
entity |
| Predicate | capitalOfJurisdictionRepresented |
P42013
|
FINISHED |
| Object | Derry |
E97019
|
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: Derry | Statement: [Mayor of Derry, capitalOfJurisdictionRepresented, Derry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capitalOfJurisdictionRepresented Context triple: [Mayor of Derry, capitalOfJurisdictionRepresented, Derry]
-
A.
capitalCityOfJurisdiction
chosen
Indicates that one entity is the primary city serving as the official capital of the specified jurisdiction or governing region.
-
B.
capitalOfJurisdictionLater
Indicates that an entity serves or served as the capital of a jurisdiction at a later time than another referenced capital relationship.
-
C.
capitalCityOfCourt
Indicates that a city serves as the official seat or capital location of a particular court.
-
D.
isLegislativeCapitalOf
Indicates that a location serves as the primary seat of a region’s legislative branch or lawmaking body.
-
E.
capitalRepresentation
Indicates that one entity serves as the capital city or capital seat representing another entity, such as a country, state, or region.
- F. None of above.
Provenance (4 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_69eefacbcc2081909ebf00daa23f1981 |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69f67f0488bc819089fbd2d2478158d3 |
completed | May 2, 2026, 10:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a129c8eec248190982b3c186929c80f |
completed | May 24, 2026, 6:37 a.m. |
| PD | Predicate disambiguation | batch_69f67e3ed894819094c067c1ef624951 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 27, 2026, 9:01 a.m.