Triple
T8318012
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TRV |
E194753
|
entity |
| Predicate | issuerProvides |
P64616
|
FINISHED |
| Object | property insurance |
—
|
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: property insurance | Statement: [TRV, issuerProvides, property insurance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: issuerProvides Context triple: [TRV, issuerProvides, property insurance]
-
A.
issuerProduces
chosen
Indicates that an issuer creates, generates, or brings into existence a particular product, document, asset, or item.
-
B.
issuerType
Indicates the classification or category of the entity that issues something (such as a document, credential, or instrument).
-
C.
issuedBy
Indicates that something (such as a document, order, or statement) has been formally created, authorized, or released by a particular agent or authority.
-
D.
issuerFounded
Indicates that one entity is the organization or person that established or created the other entity at its founding.
-
E.
issuerState
Indicates the state or jurisdiction that has issued or authorized the referenced entity (such as a document, license, or instrument).
- 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_69ca82e6e2648190a31eaf6f4f757b2a |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb7f630ea881909fb639383e60aee9 |
completed | March 31, 2026, 8:01 a.m. |
| PD | Predicate disambiguation | batch_69cb70bf689c8190a9d9b6b872abf53d |
completed | March 31, 2026, 6:59 a.m. |
Created at: March 30, 2026, 5:55 p.m.