Triple
T14243819
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Daniel Library |
E353078
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Daniel Library |
E353078
|
NE 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: Daniel Library | Statement: [Daniel Library, name, Daniel Library]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Daniel Library Context triple: [Daniel Library, name, Daniel Library]
-
A.
Daniel Library
chosen
Daniel Library is the main academic library of The Citadel, The Military College of South Carolina, serving as a central resource for research, study, and archival materials for its cadets and faculty.
-
B.
Davis Library
Davis Library is a public library branch serving the North Bethesda, Maryland community as part of the Montgomery County Public Libraries system.
-
C.
Knight Library
Knight Library is the main research library of the University of Oregon, known for its extensive academic collections and distinctive historic architecture.
-
D.
Andrews Library
Andrews Library is the main academic library of The College of Wooster, serving as a central hub for research, study, and scholarly resources on campus.
-
E.
Miller Library
Miller Library is the main academic library of Washington College, providing research resources and study spaces for its students and faculty.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d8278adc7c8190a9218d69bce3c4e6 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de6245d6a481909ef665748cd4d64c |
completed | April 14, 2026, 3:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd28235880819094f5983cce01b0fc |
completed | May 8, 2026, 12:02 a.m. |
Created at: April 10, 2026, 1:08 a.m.