Triple
T325017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thurgood Marshall College Fund |
E6494
|
entity |
| Predicate | focusesOnInstitutionControl |
P12813
|
FINISHED |
| Object | publicly supported institutions |
—
|
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: publicly supported institutions | Statement: [Thurgood Marshall College Fund, focusesOnInstitutionControl, publicly supported institutions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: focusesOnInstitutionControl Context triple: [Thurgood Marshall College Fund, focusesOnInstitutionControl, publicly supported institutions]
-
A.
institutionalControl
Indicates that one institution has governing, regulatory, or managerial authority over another entity or activity.
-
B.
involvesInstitution
Indicates that an action, event, or relationship includes or is associated with an institution as a participating party.
-
C.
hostsInstitution
Indicates that one entity serves as the hosting location or organizing body for an institution.
-
D.
establishedInstitution
Indicates that an entity founded, created, or formally set up an institution or organization.
-
E.
servesInstitution
Indicates that one entity provides services or functions in support of a particular institution.
- 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_69a2e7933d6c8190bb2592ad13286ef2 |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2eb1a37c08190b1380f6bf8513a37 |
completed | Feb. 28, 2026, 1:18 p.m. |
| PD | Predicate disambiguation | batch_69a2e949364c8190bc2351f5413f5057 |
completed | Feb. 28, 2026, 1:10 p.m. |
| PDg | Predicate description generation | batch_69a2eb18bda48190ac3d96a61a6a684d |
completed | Feb. 28, 2026, 1:18 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.