Triple

T4283504
Position Surface form Disambiguated ID Type / Status
Subject Novgorod E97210 entity
Predicate notableInstitution P7636 FINISHED
Object veche E346685 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: veche | Statement: [Novgorod, notableInstitution, veche]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: veche
Context triple: [Novgorod, notableInstitution, veche]
  • A. veche chosen
    Veche was a medieval Slavic popular assembly that functioned as a key decision-making and self-governing institution in cities like Novgorod.
  • B. Chamusca
    Chamusca is a small municipality in central Portugal known for its agricultural landscape and location along the Tagus River.
  • C. Chilia Veche
    Chilia Veche is a historic village and fishing settlement in Romania’s Danube Delta, near the border with Ukraine.
  • D. Fêtes Vénitiennes
    Fêtes Vénitiennes is a celebrated Rococo painting by Antoine Watteau that depicts an elegant outdoor gathering of masked figures in a festive, theatrical atmosphere.
  • E. Alte Feste
    Alte Feste is a historic fortress and former military headquarters in Windhoek, Namibia, now serving as a museum and prominent colonial-era landmark.
  • 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_69b3454595848190a0e6bbb6a2bea040 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b3503a84548190989a96d1a30d6ef7 completed March 12, 2026, 11:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5b7bec1a88190bd36ed6d48e1c94e completed March 14, 2026, 7:32 p.m.
Created at: March 12, 2026, 11:07 p.m.