Triple
T25152387
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cellamare |
E630111
|
entity |
| Predicate | localAdministrativeType |
P23924
|
FINISHED |
| Object | comune |
—
|
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: comune | Statement: [Cellamare, localAdministrativeType, comune]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: localAdministrativeType Context triple: [Cellamare, localAdministrativeType, comune]
-
A.
administrativelyIn
Indicates that one entity is located within or belongs to the jurisdiction or governance area of another entity for administrative purposes.
-
B.
hasAdministrativeType
chosen
Indicates that an entity is associated with a specific category or level of administrative classification (such as type of jurisdiction or administrative unit).
-
C.
districtAdministration
Indicates that an entity is responsible for managing, governing, or overseeing the administrative affairs of a specific district or local jurisdiction.
-
D.
administrativeFeature
Indicates that one entity serves as an administrative or governance-related feature, function, or attribute associated with another entity.
-
E.
administrativeName
Indicates the official name assigned to an entity within an administrative or governmental system.
- 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_69e2ff349e408190a6f4a5a66279f54d |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f46b84d59881908e038999896aa8f4 |
completed | May 1, 2026, 8:59 a.m. |
| PD | Predicate disambiguation | batch_69f45cfb53f4819099bba48c5057e787 |
completed | May 1, 2026, 7:57 a.m. |
Created at: April 18, 2026, 6:30 a.m.