Triple
T31023065
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | N-II road |
E790499
|
entity |
| Predicate | passesThroughComarca |
P33339
|
FINISHED |
| Object | Alt Empordà |
—
|
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: Alt Empordà | Statement: [N-II road, passesThroughComarca, Alt Empordà]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: passesThroughComarca Context triple: [N-II road, passesThroughComarca, Alt Empordà]
-
A.
hasComarca
chosen
Indicates that one entity is associated with, or belongs to, a specific comarca (an administrative or territorial district).
-
B.
passesThroughDistrict
Indicates that something (such as a route, boundary, or path) traverses or goes through a particular district.
-
C.
passesThroughCounty
Indicates that a route, path, or boundary traverses or goes through a specified county.
-
D.
passesThroughParish
Indicates that a route, path, or boundary physically traverses or crosses within the geographic area of a specified parish.
-
E.
passesThroughGovernorate
Indicates that something (such as a route, boundary, or flow) traverses or goes through a particular governorate.
- 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_69f224c811508190a7de096a5b1f5798 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f70e8755a48190931eaa77946f9460 |
completed | May 3, 2026, 8:59 a.m. |
| PD | Predicate disambiguation | batch_69f70abc00848190a1c3f495ef6c8dc6 |
completed | May 3, 2026, 8:43 a.m. |
Created at: April 29, 2026, 8:58 p.m.