Triple
T26091621
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Middleton, South Australia |
E658138
|
entity |
| Predicate | distanceTo Victor Harbor |
P194344
|
FINISHED |
| Object | approximately 12 kilometres |
—
|
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: approximately 12 kilometres | Statement: [Middleton, South Australia, distanceTo Victor Harbor, approximately 12 kilometres]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distanceTo Victor Harbor Context triple: [Middleton, South Australia, distanceTo Victor Harbor, approximately 12 kilometres]
-
A.
distanceFromHobart
Indicates the spatial distance between a given entity and the location of Hobart.
-
B.
distanceToWarrnambool_km
Indicates the measured distance, in kilometers, from a given entity or location to Warrnambool.
-
C.
distanceToMoruya
Indicates the measured or calculated distance between a given entity or location and Moruya.
-
D.
distanceToMelbourne
Indicates the spatial distance between a given location or entity and the city of Melbourne.
-
E.
distanceFromAlbury
Indicates the spatial distance between a given entity or location and the place named Albury.
- F. None of above. chosen
Provenance (4 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_69ee5bbfc4d08190a1b206d0ac3a1e8d |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69fd6dbd1b648190b1a0b391c03aebc5 |
completed | May 8, 2026, 4:59 a.m. |
| PD | Predicate disambiguation | batch_69fd6a9020548190bbfa845360ac85fb |
completed | May 8, 2026, 4:46 a.m. |
| PDg | Predicate description generation | batch_69fd6dbc3ac0819093fbcfe95f12b93d |
completed | May 8, 2026, 4:59 a.m. |
Created at: April 26, 2026, 7:47 p.m.