Triple

T8444340
Position Surface form Disambiguated ID Type / Status
Subject Merton College Library E199633 entity
Predicate hasPart P35 FINISHED
Object Mob Quad library E199629 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: Mob Quad library | Statement: [Merton College Library, hasPart, Mob Quad library]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mob Quad library
Context triple: [Merton College Library, hasPart, Mob Quad library]
  • A. Main Quad
    Main Quad is the principal central courtyard of University College, Oxford, around which many of the college’s key buildings are arranged.
  • B. Mob Quad chosen
    Mob Quad is one of the oldest surviving collegiate quadrangles in Oxford, notable for its medieval architecture and association with Merton College.
  • C. New Quad
    New Quad is one of the main quadrangles of Brasenose College, Oxford, providing a central courtyard space enclosed by college buildings.
  • D. New Quad
    New Quad is one of the main quadrangles of The Queen's College, Oxford, known for its collegiate architecture and central role in college life.
  • E. Quart
    Quart is a Python web microframework with an asyncio-based design that provides an ASGI-compatible, Flask-like API for building asynchronous web applications.
  • 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_69ca83170f9081909cd98f55614c6476 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe3122cfc8190ac6103fa4e4a7c45 completed March 31, 2026, 3:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce1dac8cb08190b74985a6ba3c938f completed April 2, 2026, 7:41 a.m.
Created at: March 30, 2026, 6:09 p.m.