Triple
T26029522
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kanawha |
E647389
|
entity |
| Predicate | operatedByCompanyFoundedBy |
P187360
|
FINISHED |
| Object | Marcus Garvey |
—
|
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: Marcus Garvey | Statement: [Kanawha, operatedByCompanyFoundedBy, Marcus Garvey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatedByCompanyFoundedBy Context triple: [Kanawha, operatedByCompanyFoundedBy, Marcus Garvey]
-
A.
operatedByCompanyHeadquarteredIn
Indicates that an entity is operated by a company whose headquarters is located in a specified place.
-
B.
operatedByCompany
Indicates that an entity is run, managed, or controlled by a specific company.
-
C.
alsoOperatedBy
Indicates that an entity is additionally operated or managed by another operator, alongside any primary or other operators.
-
D.
foundedCompany
Indicates that an entity established or created a company, typically as its founder or co-founder.
-
E.
commercialOperatorFoundedFor
Indicates that a commercial operator was established or created specifically for the benefit, use, or operation of the referenced entity.
- 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_69e77e8b60e88190a3b26c4f0032a2c2 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69fb563aec448190875410fb1a3ed624 |
completed | May 6, 2026, 2:54 p.m. |
| PD | Predicate disambiguation | batch_69fb35b9ede881908aaae93a215525df |
completed | May 6, 2026, 12:36 p.m. |
| PDg | Predicate description generation | batch_69fb563a28d88190b28345c465c545f8 |
completed | May 6, 2026, 2:54 p.m. |
Created at: April 22, 2026, 9:06 a.m.