Triple
T10366659
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarah Radclyffe |
E244265
|
entity |
| Predicate | leftOrganizationDate |
P2983
|
FINISHED |
| Object | early 1990s |
—
|
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: early 1990s | Statement: [Sarah Radclyffe, leftOrganizationDate, early 1990s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leftOrganizationDate Context triple: [Sarah Radclyffe, leftOrganizationDate, early 1990s]
-
A.
leftOrganization
chosen
Indicates that an entity has departed from or is no longer affiliated with a particular organization.
-
B.
createdAtOrganization
Indicates the time or context in which something was created while associated with a particular organization.
-
C.
endedOrganization
Indicates that an organization has ceased to exist or operate, marking the termination of its existence or activities.
-
D.
institutionDate
Indicates the date on which an institution (such as an organization, law, or formal body) was officially established or came into existence.
-
E.
originalOrganization
Indicates the organization from which an entity (such as a person, document, or resource) initially originated or was first associated.
- 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_69d381b3e328819094b23b8edcd29b5a |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e96fd6f081908f630a16106996d9 |
completed | April 7, 2026, 11:24 a.m. |
| PD | Predicate disambiguation | batch_69d4dface5508190a7b42f01ad0a19a2 |
completed | April 7, 2026, 10:42 a.m. |
Created at: April 6, 2026, noon