Triple
T25717537
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Linky |
E644899
|
entity |
| Predicate | meterLocation |
P159009
|
FINISHED |
| Object | customer premises |
—
|
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: customer premises | Statement: [Linky, meterLocation, customer premises]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: meterLocation Context triple: [Linky, meterLocation, customer premises]
-
A.
mineLocation
Indicates that a specified location is the site where a particular mine (e.g., resource extraction or explosive device) is situated.
-
B.
mapLocation
Indicates a relationship where an entity is associated with a specific position or area on a map.
-
C.
cityLocation
Indicates that a city is geographically situated within or associated with a specific larger area or place.
-
D.
eraLocation
Indicates the place or geographic context in which a particular historical era or time period occurs or is primarily associated.
-
E.
coordinateLocation
Indicates that an entity is located at, or associated with, a specific geographic coordinate or set of coordinates.
- 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_69e77e8476fc8190bd5e9d05b89fad0a |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f5fc6365288190ac46e37a887aa1e1 |
completed | May 2, 2026, 1:30 p.m. |
| PD | Predicate disambiguation | batch_69f480824a1c81908a8a492eedbc2596 |
completed | May 1, 2026, 10:29 a.m. |
| PDg | Predicate description generation | batch_69f48b9058d081908ec9af261ee092e2 |
completed | May 1, 2026, 11:16 a.m. |
Created at: April 21, 2026, 9:46 p.m.