Triple
T23409735
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thirty Years' View |
E560032
|
entity |
| Predicate | documentsInstitution |
P82572
|
FINISHED |
| Object | United States Congress |
—
|
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: United States Congress | Statement: [Thirty Years' View, documentsInstitution, United States Congress]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: documentsInstitution Context triple: [Thirty Years' View, documentsInstitution, United States Congress]
-
A.
documentsCommunity
Indicates that an entity records, describes, or provides information about a particular community.
-
B.
documentsActivity
chosen
Indicates that one entity records, describes, or provides evidence of an activity performed by another entity.
-
C.
academicIntegrationWithColumbia
Indicates a formal academic collaboration or integration relationship established with Columbia University, such as shared programs, courses, or institutional affiliations.
-
D.
inInstitution
Indicates that an entity is located within, belongs to, or is formally associated with a particular institution.
-
E.
documentsJourneyTo
Indicates that one entity records or describes the travel, route, or progression of another entity from one place or state to another.
- 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_69e2454b3a5881909c64773dc8a5d289 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a510b3848190ae42679ef0bcd424 |
completed | April 29, 2026, 6:28 a.m. |
| PD | Predicate disambiguation | batch_69f061ed34288190a2e5e8cae03b0095 |
completed | April 28, 2026, 7:29 a.m. |
Created at: April 17, 2026, 5:38 p.m.