Triple

T11129095
Position Surface form Disambiguated ID Type / Status
Subject Star Street E263230 entity
Predicate connectsTo P845 FINISHED
Object Manger Square E47680 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: Manger Square | Statement: [Star Street, connectsTo, Manger Square]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Manger Square
Context triple: [Star Street, connectsTo, Manger Square]
  • A. Manger Square chosen
    Manger Square is the central plaza in Bethlehem, renowned as a major Christian pilgrimage site adjacent to the Church of the Nativity, traditionally believed to mark the birthplace of Jesus.
  • B. Royal Square
    Royal Square is a notable public square in Brussels, Belgium, known for its neoclassical architecture and central role in the city's historic upper town.
  • C. Royal Square
    Royal Square is the English name for Plaça Reial, a famous neoclassical square in Barcelona known for its palm trees, arcades, and vibrant nightlife.
  • D. Teele Square
    Teele Square is a commercial and residential neighborhood hub in Somerville, Massachusetts, known for its local shops, restaurants, and proximity to Tufts University.
  • E. Princess Square
    Princess Square is a central shopping centre in Bracknell, England, featuring a range of retail stores and services.
  • 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_69d6aa9c0ba08190bbd19c217489b755 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e830e804819097fcc3826d84dab8 completed April 9, 2026, 5:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69e496b4cadc8190b82ac12061c31bdc completed April 19, 2026, 8:47 a.m.
Created at: April 8, 2026, 9:28 p.m.