Triple

T16764468
Position Surface form Disambiguated ID Type / Status
Subject Prague 1 E407427 entity
Predicate contains P35 FINISHED
Object Old Town Square E89484 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: Old Town Square | Statement: [Prague 1, contains, Old Town Square]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Old Town Square
Context triple: [Prague 1, contains, Old Town Square]
  • A. Old Town Square chosen
    Old Town Square is a historic central plaza in Prague renowned for its medieval architecture, Astronomical Clock, and vibrant cultural atmosphere.
  • B. Old Town Square
    Old Town Square is a central pedestrian plaza in downtown Fort Collins, Colorado, known for its historic architecture, shops, restaurants, and community events.
  • C. Charles Square
    Charles Square is one of the largest historic squares in Prague, serving as a major public space and transport hub in the city’s New Town.
  • D. Rynok Square
    Rynok Square is the historic central square of Lviv, Ukraine, known for its Renaissance and Baroque townhouses, lively cafés, and role as the city’s cultural and social hub.
  • E. Tykocin Market Square
    Tykocin Market Square is a historic central plaza in the town of Tykocin, Poland, known for its well-preserved architecture and traditional small-town charm.
  • 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_69d8839174188190909f190097207065 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3abef492c8190880d3b39c3641eed completed April 18, 2026, 4:06 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00a52ff9d481909675c7e1f81191dc completed May 10, 2026, 3:33 p.m.
Created at: April 10, 2026, 5:21 a.m.