Triple
T17373217
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Williams College Libraries |
E422367
|
entity |
| Predicate | primaryServiceTo |
P1296
|
FINISHED |
| Object | Williams College 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: Williams College students | Statement: [Williams College Libraries, primaryServiceTo, Williams College students]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryServiceTo Context triple: [Williams College Libraries, primaryServiceTo, Williams College students]
-
A.
primaryService
Indicates that one entity serves as the main or principal service provided or used in relation to another entity.
-
B.
primaryServicePattern
Indicates the main or most typical way in which a service is delivered, structured, or utilized within a given context.
-
C.
primaryServiceRole
Indicates the main or most important functional role that a service performs in relation to other entities or processes.
-
D.
primaryFor
Indicates that one entity serves as the main or principal option, resource, or association for another entity among possible alternatives.
-
E.
primaryServes
chosen
Indicates that one entity’s main or principal function is to serve, support, or provide service to another entity.
- 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_69d889d6535c81908be333c01deaec4e |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a6a9ec881908bfe49413826d37e |
completed | April 19, 2026, 2:14 a.m. |
| PD | Predicate disambiguation | batch_69e3b02ac8688190a7182f1b2151d721 |
completed | April 18, 2026, 4:24 p.m. |
Created at: April 10, 2026, 5:44 a.m.