Triple

T9621470
Position Surface form Disambiguated ID Type / Status
Subject Sari (place name) E232350 entity
Predicate refersTo P37 FINISHED
Object Sari, Iran E810198 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: Sari, Iran | Statement: [Sari (place name), refersTo, Sari, Iran]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sari, Iran
Context triple: [Sari (place name), refersTo, Sari, Iran]
  • A. Sari, Mazandaran chosen
    Sari, Mazandaran is a major city in northern Iran and the capital of Mazandaran Province, known for its historical sites and proximity to the Caspian Sea.
  • B. Sabah Iranun
    Sabah Iranun is a regional dialect of the Iranun language spoken primarily by Iranun communities in the Malaysian state of Sabah.
  • C. Iranshahr
    Iranshahr is a city in southeastern Iran known as an administrative and cultural center within the Sistan and Baluchestan region.
  • D. Mozzafarieh
    Mozzafarieh is a notable section of the Tabriz Historic Bazaar Complex, traditionally associated with specialized trade and craftsmanship within the bazaar.
  • E. Sari, Afghanistan
    Sari, Afghanistan is a small settlement in Afghanistan whose name is shared with other similarly named places in the region.
  • 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_69ca84867bb88190b4b57dd5a56d5691 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9ad3a8d88190b1414aa676d82f36 completed April 1, 2026, 10:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69d18225f9508190bde23b9d2a40bccc completed April 4, 2026, 9:27 p.m.
Created at: March 30, 2026, 8:10 p.m.