Triple
T20059708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Metlink |
E499434
|
entity |
| Predicate | contractsOperators |
P15881
|
FINISHED |
| Object | bus companies in Wellington Region |
—
|
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: bus companies in Wellington Region | Statement: [Metlink, contractsOperators, bus companies in Wellington Region]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: contractsOperators Context triple: [Metlink, contractsOperators, bus companies in Wellington Region]
-
A.
contractUnit
chosen
Indicates that one entity serves as a contractual unit or party within a contract relationship involving another entity.
-
B.
contractFeature
Indicates that one entity is a feature, term, or provision that is included in or associated with a particular contract.
-
C.
coOperator
Indicates that two or more entities work together as partners or collaborators in performing an activity or achieving a shared objective.
-
D.
otherOperator
Indicates a relationship where one operator is distinguished from, or serves as an alternative to, another operator within the same context or system.
-
E.
hasOperatorContractStart
Indicates the date on which an operator’s contractual agreement with another entity begins.
- 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_69da6276bcf48190aabbf279192a5fb4 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66374f4a48190beb575a6c84ebdb4 |
completed | April 20, 2026, 5:33 p.m. |
| PD | Predicate disambiguation | batch_69e54cee7a5c819084ae4ff26419833f |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 3:38 p.m.