Triple
T33469876
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Istituto Nazionale delle Assicurazioni |
E857156
|
entity |
| Predicate | hasMainClientBase |
P203070
|
FINISHED |
| Object | Italian citizens |
—
|
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: Italian citizens | Statement: [Istituto Nazionale delle Assicurazioni, hasMainClientBase, Italian citizens]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMainClientBase Context triple: [Istituto Nazionale delle Assicurazioni, hasMainClientBase, Italian citizens]
-
A.
hasClient
Indicates that an entity maintains a client relationship with another entity, typically as a provider of goods or services.
-
B.
hasMainHost
Indicates that one entity serves as the primary or principal host for another entity.
-
C.
hasMainVoterBase
Indicates that an entity (such as a political party or candidate) has its primary or most significant group of supporters in a particular population or region.
-
D.
hasClientProgram
Indicates that an entity (such as a service, system, or organization) is associated with or uses a specific client program.
-
E.
hasMainArch
Indicates that an entity possesses or features a primary or central arch structure.
- 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_69f34973461481909c701c98ebd75623 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a011c64ff18819099195701bbecbb20 |
completed | May 11, 2026, 12:01 a.m. |
| PD | Predicate disambiguation | batch_6a011b7f7a508190b2ebb518fb7a2fe9 |
completed | May 10, 2026, 11:57 p.m. |
| PDg | Predicate description generation | batch_6a011c645b68819092ccbb14c1a4c454 |
completed | May 11, 2026, 12:01 a.m. |
Created at: May 1, 2026, 1:37 a.m.