Triple
T507
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harvard University |
E9
|
entity |
| Predicate | hasLibraryCollection |
P105
|
FINISHED |
| Object | millions of volumes |
—
|
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: millions of volumes | Statement: [Harvard University, hasLibraryCollection, millions of volumes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLibraryCollection Context triple: [Harvard University, hasLibraryCollection, millions of volumes]
-
A.
hasPart
Indicates that one entity is a component, segment, or constituent part of another entity.
-
B.
hasPublication
Indicates that an entity is associated with or responsible for a specific publication.
-
C.
hasRepresentationIn
Indicates that one entity is represented, depicted, or encoded within another entity, such as a concept, object, or data structure having a corresponding representation in a specific medium or context.
-
D.
hasNotableFacility
chosen
Indicates that an entity possesses or hosts a facility that is of particular significance, prominence, or interest.
-
E.
hasAlumni
Indicates that an institution or organization is associated with individuals who formerly attended or graduated from it.
- 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_69a22735e1b081908bd0457057dcf086 |
completed | Feb. 27, 2026, 11:22 p.m. |
| NER | Named-entity recognition | batch_69a2304aaa2c8190ab7e8dd5da977c11 |
completed | Feb. 28, 2026, 12:01 a.m. |
| PD | Predicate disambiguation | batch_69a22918087081909e717b8bee896e8f |
completed | Feb. 27, 2026, 11:30 p.m. |
Created at: Feb. 27, 2026, 11:24 p.m.