Triple

T14781491
Position Surface form Disambiguated ID Type / Status
Subject Zugot E347399 entity
Predicate typicalOffices P5164 FINISHED
Object Nasi E906783 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: Nasi | Statement: [Zugot, typicalOffices, Nasi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nasi
Context triple: [Zugot, typicalOffices, Nasi]
  • A. Nasi chosen
    Nasi is the Hebrew title for a high-ranking leader or prince, historically used for the head of the Jewish community or Sanhedrin.
  • B. nasi liwet
    Nasi liwet is a fragrant Indonesian rice dish, often cooked in coconut milk and spices and served communally with assorted side dishes, particularly associated with Sundanese and Javanese culinary traditions.
  • C. Arzo
    Arzo is a village and former municipality in the canton of Ticino in southern Switzerland, now part of the municipality of Mendrisio.
  • D. Soppeng
    Soppeng is a historical region and former kingdom in South Sulawesi, Indonesia, known for its Bugis culture and role in regional politics.
  • E. Sarilamak
    Sarilamak is a town in West Sumatra, Indonesia, that serves as the administrative center of Lima Puluh Kota Regency.
  • 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_69d822e9b9e08190bedcc31a163fda82 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deca9de3f48190b7706925e2947cf5 completed April 14, 2026, 11:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe0d02e28081909a11d6e6fdb8d28c completed May 8, 2026, 4:19 p.m.
Created at: April 10, 2026, 1:31 a.m.