Triple
T10982649
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jagger Library |
E259546
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Jagger Library |
E259546
|
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: Jagger Library | Statement: [Jagger Library, name, Jagger Library]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jagger Library Context triple: [Jagger Library, name, Jagger Library]
-
A.
Jagger Library
chosen
Jagger Library is a historic research library at the University of Cape Town, renowned for its extensive African studies and archival collections.
-
B.
Scott Library
Scott Library is a major academic library located on York University’s Keele Campus in Toronto, serving as a central resource for research and study.
-
C.
Lee Library
Lee Library is a historic public library building and cultural landmark located in the town of Lee, Massachusetts.
-
D.
Wilson Library
Wilson Library is the main historic research library and iconic neoclassical centerpiece of the University of North Carolina at Chapel Hill campus.
-
E.
Farber Library
Farber Library is a main library building at Brandeis University that houses a large portion of the university’s academic collections and study spaces.
- 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_69d6aa895f4c8190887a15460ef622f4 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d772eb518c8190a885a417815f2ff6 |
completed | April 9, 2026, 9:35 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e344c77d6c8190a9b5e2cc967fb031 |
completed | April 18, 2026, 8:45 a.m. |
Created at: April 8, 2026, 9:24 p.m.