Triple
T10167409
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Low Plaza |
E235240
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Kent Hall |
E237065
|
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: Kent Hall | Statement: [Low Plaza, near, Kent Hall]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kent Hall Context triple: [Low Plaza, near, Kent Hall]
-
A.
Kent Hall
chosen
Kent Hall is an academic building at Columbia University’s Morningside Heights campus, historically associated with housing language and international studies departments.
-
B.
Checker Hall
Checker Hall is a surviving medieval building that once formed part of the historic Abingdon Abbey complex in Oxfordshire, England.
-
C.
Jane Hall
Jane Hall was the wife of British Royal Navy admiral Sir Edward Codrington, noted for her connection to this prominent naval figure of the early 19th century.
-
D.
Jane Hall
Jane Hall was an actress known for appearing in early 20th-century American silent films.
-
E.
Blue Hall
Blue Hall is an ornately decorated ceremonial room within Tehran’s historic Niavaran Palace complex, noted for its rich blue-themed interior and use in official receptions.
- 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_69ca84ceafd0819085828600e11bed6b |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdec6e016c81909ded2a16b839c405 |
completed | April 2, 2026, 4:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d354fc0a808190aa57b68708d91590 |
completed | April 6, 2026, 6:38 a.m. |
Created at: March 30, 2026, 9:10 p.m.