Triple
T12888566
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrew Mack |
E308296
|
entity |
| Predicate | foundedCompanyOpeningYear |
P4025
|
FINISHED |
| Object | 1997 |
—
|
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: 1997 | Statement: [Andrew Mack, foundedCompanyOpeningYear, 1997]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: foundedCompanyOpeningYear Context triple: [Andrew Mack, foundedCompanyOpeningYear, 1997]
-
A.
foundedCompany
Indicates that an entity established or created a company, typically as its founder or co-founder.
-
B.
foundedAt
chosen
Indicates the time or date at which an entity (such as an organization, project, or institution) was established or created.
-
C.
companyFoundedWith
Indicates that a company was established using or in association with a particular resource, organization, or founding context.
-
D.
organizationTypeFounded
Indicates the type or category of organization that was established or created in a founding event.
-
E.
foundedInYearApprox
Indicates that an entity was established or came into existence around an approximate year, rather than on a precisely known date.
- 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_69d7bdf7c1f0819098102569a8d8cbf5 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97c7f91d08190aac2f6419d3ba992 |
completed | April 10, 2026, 10:41 p.m. |
| PD | Predicate disambiguation | batch_69d96fa55b888190ab1612e93c41aec4 |
completed | April 10, 2026, 9:46 p.m. |
Created at: April 9, 2026, 5:39 p.m.