Triple
T33589593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | INSU |
E860379
|
entity |
| Predicate | parentOrganizationAcronym |
P7408
|
FINISHED |
| Object | CNRS |
—
|
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: CNRS | Statement: [INSU, parentOrganizationAcronym, CNRS]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: parentOrganizationAcronym Context triple: [INSU, parentOrganizationAcronym, CNRS]
-
A.
parentOrganizationAbbreviation
chosen
Indicates that the object is the abbreviated name or acronym of the subject’s parent organization.
-
B.
organizationAcronym
Indicates that an organization is known or referred to by a specific acronym.
-
C.
parentOrganization
Indicates that one organization is the higher-level or owning entity in an organizational hierarchy relative to another organization.
-
D.
relatedOrganizationAbbreviation
Indicates that one organization is associated with another through a specific abbreviated form of its name or title.
-
E.
parentOrganizationField
Indicates that the field specifies or references the organization that serves as the parent or higher-level entity of another organization.
- 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_69f3497e70e48190951c94d072879bec |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fd553d7cb881908d243e7a9f30ac85 |
completed | May 8, 2026, 3:15 a.m. |
| PD | Predicate disambiguation | batch_69fd514dcb1c81908333c70d7edd79c9 |
completed | May 8, 2026, 2:58 a.m. |
Created at: May 1, 2026, 1:40 a.m.