Triple
T32093121
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2017 British & Irish Lions tour to New Zealand |
E819647
|
entity |
| Predicate | secondTestCity |
P156357
|
FINISHED |
| Object | Wellington |
—
|
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: Wellington | Statement: [2017 British & Irish Lions tour to New Zealand, secondTestCity, Wellington]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondTestCity Context triple: [2017 British & Irish Lions tour to New Zealand, secondTestCity, Wellington]
-
A.
secondMetropolitan
Indicates that one entity is the second metropolitan (e.g., second-ranking or second-designated metropolitan authority or see) in relation to another entity.
-
B.
secondTestVenue
chosen
Indicates that an entity serves as the second venue or location associated with a particular test or testing event.
-
C.
secondFightCity
Indicates that an entity engaged in its second fight or battle in the specified city.
-
D.
isSecondLevelCityIn
Indicates that a city is classified as a second-level city within a specified administrative or territorial region.
-
E.
secondTestName
Indicates that an entity serves as the second named test or secondary test designation associated with another entity.
- 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_69f349004b2481908ce2e50af0d579a8 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fe779248c081909f0ed1a2a0df23db |
completed | May 8, 2026, 11:53 p.m. |
| PD | Predicate disambiguation | batch_69fe76eaf6d48190998bc7168749cc42 |
completed | May 8, 2026, 11:51 p.m. |
Created at: May 1, 2026, 12:25 a.m.