Triple
T12185648
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Levin |
E290326
|
entity |
| Predicate | distanceFromPalmerstonNorth |
P52211
|
FINISHED |
| Object | about 50 km southwest |
—
|
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: about 50 km southwest | Statement: [Levin, distanceFromPalmerstonNorth, about 50 km southwest]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distanceFromPalmerstonNorth Context triple: [Levin, distanceFromPalmerstonNorth, about 50 km southwest]
-
A.
distanceToPalmerstonNorth
chosen
Indicates the spatial distance between a given location and Palmerston North.
-
B.
distanceToWellington
Indicates the measured distance between a given entity’s location and the location of Wellington.
-
C.
distanceFromAuckland_km
Indicates the physical distance, measured in kilometers, between an entity’s location and Auckland.
-
D.
distanceToChristchurch
Indicates the spatial distance between a given entity’s location and the location of Christchurch.
-
E.
distanceFromNewZealandMainland_km
Indicates the distance, measured in kilometers, between an entity’s location and the mainland of New Zealand.
- 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_69d6ab64de5881908d56eb7a75c6cc69 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d91a83012c81908d04bbab5fdcd8c2 |
completed | April 10, 2026, 3:42 p.m. |
| PD | Predicate disambiguation | batch_69d91510a258819090ef8fbdc2d8707b |
completed | April 10, 2026, 3:19 p.m. |
Created at: April 8, 2026, 9:50 p.m.