Triple
T23808920
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Christchurch East |
E589791
|
entity |
| Predicate | hasElectorateNameOrigin |
P24038
|
FINISHED |
| Object | eastern part of Christchurch |
—
|
LITERAL 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: eastern part of Christchurch | Statement: [Christchurch East, hasElectorateNameOrigin, eastern part of Christchurch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasElectorateNameOrigin Context triple: [Christchurch East, hasElectorateNameOrigin, eastern part of Christchurch]
-
A.
hasNameOrigin
Indicates that the origin or source of an entity’s name is specified by the related entity.
-
B.
hasEpithetOrigin
Indicates that the origin or source of an epithet (a descriptive name or label) is specified for an entity.
-
C.
electoralNameUsedFor
Indicates that a particular electoral name or designation is used to refer to or identify a given entity in an electoral context.
-
D.
electorateCreatedFrom
Indicates that a particular electorate or voting district was formed by dividing, merging, or otherwise deriving it from another electoral unit.
-
E.
districtNameOrigin
chosen
Indicates that the relationship specifies the origin or source from which a district’s name is derived.
- 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_69e25d19fecc8190a5cf39bbb18d5d7f |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c753c46081908b3c9e5c2517b051 |
completed | April 29, 2026, 8:54 a.m. |
| PD | Predicate disambiguation | batch_69f155fe300481909bd617443228df65 |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 7:56 p.m.