Triple
T36944677
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apulian coast |
E913871
|
entity |
| Predicate | regionCapitalOnCoast |
P180849
|
FINISHED |
| Object | Bari |
—
|
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: Bari | Statement: [Apulian coast, regionCapitalOnCoast, Bari]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regionCapitalOnCoast Context triple: [Apulian coast, regionCapitalOnCoast, Bari]
-
A.
hasCapitalCityOnCoast
chosen
Indicates that the capital city of an entity is geographically located on a coastline.
-
B.
countryCapitalCoastline
Indicates that a country's capital city is located on or directly adjacent to a coastline.
-
C.
coastalStateCapital
Indicates that the subject is the capital city of a state that is located on or directly adjacent to a sea or ocean coastline.
-
D.
isCoastalSettlementOf
Indicates that a settlement is located on or near the coast within the territory of a specified geographic or administrative area.
-
E.
bordersCityViaCoast
Indicates that a city is adjacent to a body of water in such a way that its boundary with that water forms part of the city’s coastal border.
- 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_69f76e8a6a5c81909c1febf32bf3fe23 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a00474f08908190bc8ae3b320ec887b |
completed | May 10, 2026, 8:52 a.m. |
| PD | Predicate disambiguation | batch_6a0045dc3bd48190a9e0520f3ef3f067 |
completed | May 10, 2026, 8:46 a.m. |
Created at: May 3, 2026, 4:13 p.m.