Triple
T27972515
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Lever, 1st Viscount Leverhulme |
E706399
|
entity |
| Predicate | companyEventuallyBecame |
P58574
|
FINISHED |
| Object | Unilever |
—
|
NE NERFINISHED |
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: Unilever | Statement: [William Lever, 1st Viscount Leverhulme, companyEventuallyBecame, Unilever]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: companyEventuallyBecame Context triple: [William Lever, 1st Viscount Leverhulme, companyEventuallyBecame, Unilever]
-
A.
companyEvolvedInto
chosen
Indicates that one company has transformed, restructured, or transitioned over time into another company, representing a continuity of organizational identity or operations.
-
B.
companyRenamedBackTo
Indicates that a company reverted its name from a newer one back to a previous or original name.
-
C.
companyRenamedTo
Indicates that a company has changed its official name from a previous one to a new specified name.
-
D.
organizationEvolvedInto
Indicates that one organization has transformed, restructured, or otherwise changed over time to become another organization.
-
E.
succeededByCompanyName
Indicates that one company is followed or replaced by another company as its successor.
- 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_69ef96b7f330819090f315318ba6977e |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69f6b2a65c7c8190ac40f1466ceadefc |
completed | May 3, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f6b14d7d508190bc7d4c89dfba4a32 |
completed | May 3, 2026, 2:22 a.m. |
Created at: April 27, 2026, 7:39 p.m.