Triple
T573925
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gutman Library |
E13721
|
entity |
| Predicate | userGroupServed |
P14200
|
FINISHED |
| Object | students of Harvard Graduate School of Education |
—
|
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: students of Harvard Graduate School of Education | Statement: [Gutman Library, userGroupServed, students of Harvard Graduate School of Education]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: userGroupServed Context triple: [Gutman Library, userGroupServed, students of Harvard Graduate School of Education]
-
A.
servesUsers
chosen
Indicates that an entity provides services, functionality, or benefits to one or more users.
-
B.
servesRole
Indicates that one entity performs, fulfills, or occupies a particular function, position, or responsibility in relation to another entity.
-
C.
userBase
Indicates that one entity serves as the primary or foundational group of users associated with another entity.
-
D.
servesUnder
Indicates that one entity works in a subordinate role under the authority, command, or supervision of another entity.
-
E.
hasSupporterGroup
Indicates that an entity is associated with a group of supporters that backs, promotes, or advocates for 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_69a4933fa4d88190a7949cc83c08c5c1 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49b4ae0988190bdd0ad428b784d85 |
completed | March 1, 2026, 8:02 p.m. |
| PD | Predicate disambiguation | batch_69a494c4969c819080375d08f9eec50c |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:33 p.m.