Triple
T31660002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Randolph |
E807972
|
entity |
| Predicate | regionOfArrival |
P1522
|
FINISHED |
| Object | Canterbury, New Zealand |
—
|
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: Canterbury, New Zealand | Statement: [Randolph, regionOfArrival, Canterbury, New Zealand]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regionOfArrival Context triple: [Randolph, regionOfArrival, Canterbury, New Zealand]
-
A.
placeOfArrival
chosen
Indicates the location at which an entity or person arrives at the end of a journey, movement, or transfer.
-
B.
regionOfMigration
Indicates the geographic area from which an entity or population moves or migrates.
-
C.
regionFrom
Indicates that something originates from, is derived from, or is associated with a particular geographic or administrative region.
-
D.
departurePortRegion
Indicates the geographic region from which a departure (such as a trip, shipment, or transport) originates.
-
E.
historicalTerritoryOfArrival
Indicates that a location served as the territory where an entity historically arrived or first came to be present.
- 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_69f348daf95c81908b4c985b7ddcd0b3 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69fe991bca608190b524e419642f4243 |
completed | May 9, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69fe979fc1c4819091fc48d63ea12063 |
completed | May 9, 2026, 2:10 a.m. |
Created at: April 30, 2026, 10:56 p.m.