Triple
T5417
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harvard Library |
E106
|
entity |
| Predicate | primaryUsers |
P98
|
FINISHED |
| Object | Harvard University students |
—
|
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: Harvard University students | Statement: [Harvard Library, primaryUsers, Harvard University students]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryUsers Context triple: [Harvard Library, primaryUsers, Harvard University students]
-
A.
parent
Indicates a relationship where one entity is the direct mother or father of another entity, from whom that other entity is descended.
-
B.
usedFor
chosen
Indicates that one entity serves a purpose, function, or role in accomplishing, enabling, or supporting another entity or activity.
-
C.
keyPerson
Indicates that a person plays a primary, central, or critically important role in relation to an organization, project, or entity.
-
D.
advocates
Indicates that one entity publicly supports, recommends, or argues in favor of another entity or its interests.
-
E.
fullName
Indicates that an entity has a complete personal name, typically combining given name(s) and family name into a single string.
- 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_69a238d6b47881909e68288aed2fd858 |
completed | Feb. 28, 2026, 12:37 a.m. |
| NER | Named-entity recognition | batch_69a23c24b3d08190a714126292fd5479 |
completed | Feb. 28, 2026, 12:51 a.m. |
| PD | Predicate disambiguation | batch_69a23998af288190855f0456740cbd51 |
completed | Feb. 28, 2026, 12:40 a.m. |
Created at: Feb. 28, 2026, 12:40 a.m.