Triple

T14675222
Position Surface form Disambiguated ID Type / Status
Subject Old Church E344618 entity
Predicate hasName P744 FINISHED
Object Old Church unclear NED1 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 Church | Statement: [Old Church, hasName, Old Church]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Old Church
Context triple: [Old Church, hasName, Old Church]
  • A. Old Church
    Old Church is a historic Gothic-style church in Delft, Netherlands, renowned for its leaning tower and as the burial place of notable Dutch figures.
  • B. Old Church
    Old Church is the English name for the Oude Kerk, Amsterdam’s oldest surviving building and a historic Protestant church located in the city’s Red Light District.
  • C. Old Cathedral
    The Old Cathedral in Linz is a historic Baroque church and prominent religious landmark in the city’s center.
  • D. Old Cathedral
    Old Cathedral is a historic Catholic church and landmark in Vincennes, Indiana, notable as one of the oldest churches in the state and a key site in the region’s early religious and civic history.
  • E. Old Chapel
    Old Chapel is a historic early American church and burial ground in Millwood, Virginia, notable for its colonial-era architecture and long-standing religious significance.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide. chosen

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_69d822e283fc8190a0e4c235cf880052 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb5666e648190b5faa07076f497b8 completed April 14, 2026, 9:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fde17c24e0819089dd9606298f5ac9 completed May 8, 2026, 1:13 p.m.
Created at: April 10, 2026, 1:27 a.m.