Triple
T3524025
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Willis Group Holdings |
E74494
|
entity |
| Predicate | providesProduct |
P10882
|
FINISHED |
| Object | property and casualty insurance brokerage |
—
|
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 and casualty insurance brokerage | Statement: [Willis Group Holdings, providesProduct, property and casualty insurance brokerage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: providesProduct Context triple: [Willis Group Holdings, providesProduct, property and casualty insurance brokerage]
-
A.
offersProduct
chosen
Indicates that one entity makes a product available to another entity, typically for sale or use.
-
B.
hasProduct
Indicates that an entity possesses, offers, or is associated with a particular product.
-
C.
productForm
Indicates the specific physical or presentation format in which a product is offered or delivered (e.g., tablet, liquid, package type).
-
D.
providesThat
Indicates that one entity stipulates, specifies, or sets forth a condition, rule, or provision that applies to another entity or situation.
-
E.
exportProduct
Indicates that an entity sends or sells a product from its own country or region to another country or external market.
- 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_69ad85d0c5488190a3d8e02ebd01a1aa |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbc68b15881909b407486946ec3c5 |
completed | March 8, 2026, 6:14 p.m. |
| PD | Predicate disambiguation | batch_69adae121a048190b03825a001d21f49 |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:19 p.m.