Triple

T13383008
Position Surface form Disambiguated ID Type / Status
Subject Law Tower E319365 entity
Predicate name P16 FINISHED
Object Law Tower E319365 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: Law Tower | Statement: [Law Tower, name, Law Tower]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Law Tower
Context triple: [Law Tower, name, Law Tower]
  • A. Law Tower chosen
    Law Tower is the iconic high-rise building that houses Boston University School of Law on the university’s Charles River Campus in Boston, Massachusetts.
  • B. Goodwin Building
    The Goodwin Building is a historic wing of the Wadsworth Atheneum Museum of Art in Hartford, Connecticut, housing part of the museum’s art collections and galleries.
  • C. Proctor Law Building
    The Proctor Law Building is a historic legal office structure in Lumberton, North Carolina, recognized for its architectural and local civic significance.
  • D. Sterling Law Building
    The Sterling Law Building is a prominent Collegiate Gothic structure at Yale University that houses Yale Law School.
  • E. Eldon Building
    Eldon Building is a key academic facility at the University of Portsmouth, primarily housing the university’s creative and cultural industries departments.
  • 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_69d806b886bc8190b676e7768b8e01c5 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dadce80158819082156eaeaeda3bd8 completed April 11, 2026, 11:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7268cf04c8190a35fd48ce81c149e completed May 3, 2026, 10:42 a.m.
Created at: April 9, 2026, 9:33 p.m.