Triple

T15240769
Position Surface form Disambiguated ID Type / Status
Subject Lucca E364247 entity
Predicate near P350 FINISHED
Object Pisa E32982 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: Pisa | Statement: [Lucca, near, Pisa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pisa
Context triple: [Lucca, near, Pisa]
  • A. Pisa
    Pisa is an ancient city in the Peloponnese region of Greece, historically significant as a center near Olympia and associated with early Greek myth and athletics.
  • B. Pisa chosen
    Pisa is a historic Italian city in Tuscany best known for its iconic Leaning Tower and as a significant center of medieval trade, learning, and architecture.
  • C. Florence
    Florence is the birth name of Elizabeth Arden, the pioneering Canadian-American businesswoman who founded the iconic Elizabeth Arden cosmetics brand.
  • D. Florence
    Florence is a critically acclaimed interactive story and mobile video game that explores the emotional journey of a young woman's first love through minimalist gameplay and visual storytelling.
  • E. Florence
    Florence is an unincorporated community within Florence Township in New Jersey, known primarily as a residential area along the Delaware River.
  • 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_69d85a0dde7481908fc64d1e82d5d20d completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e007db9a148190aadea8d5f8b6b261 completed April 15, 2026, 9:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69ff01de4ccc8190aeac4a6c1ffc08d9 completed May 9, 2026, 9:43 a.m.
Created at: April 10, 2026, 3:13 a.m.