Triple
T1088666
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St Kilda |
E24109
|
entity |
| Predicate | distanceToOuterHebrides |
P23347
|
FINISHED |
| Object | about 64 kilometres west of Benbecula |
—
|
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 64 kilometres west of Benbecula | Statement: [St Kilda, distanceToOuterHebrides, about 64 kilometres west of Benbecula]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distanceToOuterHebrides Context triple: [St Kilda, distanceToOuterHebrides, about 64 kilometres west of Benbecula]
-
A.
distanceFromEdinburghApprox
Indicates that an entity is located at an approximate distance from Edinburgh, rather than an exact measured distance.
-
B.
distanceFromGlasgow
Indicates the spatial distance separating a given entity or location from Glasgow.
-
C.
distanceToSaintHelena
Indicates the measured distance between a given entity and the location of Saint Helena.
-
D.
distanceToKirkcaldy
Indicates the spatial distance between a given entity and the location of Kirkcaldy.
-
E.
distanceToDundee
Indicates the measured spatial distance between a given entity and the location of Dundee.
- 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_69a49404428c819092dcc9632f5f7b8b |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b97d85708190a1630256648aa4a2 |
completed | March 1, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69a4b741b0cc8190be001a16a81f6d9e |
completed | March 1, 2026, 10:01 p.m. |
| PDg | Predicate description generation | batch_69a4b7bd3d50819091e6f1d2ffe4c7ee |
completed | March 1, 2026, 10:03 p.m. |
Created at: March 1, 2026, 7:42 p.m.