Triple

T8159667
Position Surface form Disambiguated ID Type / Status
Subject Mazandaran Province E190543 entity
Predicate hasCity P316 FINISHED
Object Neka
Neka is a city in northern Iran known for its location near the Caspian Sea and its role as an industrial and agricultural center in Mazandaran Province.
 E715269 NE FINISHED

How this triple was built (4 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: Neka | Statement: [Mazandaran Province, hasCity, Neka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Neka
Context triple: [Mazandaran Province, hasCity, Neka]
  • A. Nese
    Nese is an endangered Oceanic language spoken by a small community on the island of Malakula in Vanuatu.
  • B. Neyo
    Ne-Yo is an American R&B singer, songwriter, and record producer known for hits like "So Sick" and "Closer" and for writing songs for numerous major artists.
  • C. Némi
    Némi is an Oceanic language spoken by a small indigenous community in New Caledonia.
  • D. Nele
    Nele is a Kannada novel by acclaimed Indian writer S. L. Bhyrappa, known for its philosophical depth and exploration of human values.
  • E. Nane
    Nane is a Swedish lawyer and artist best known as the widow of former United Nations Secretary-General Kofi Annan.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Neka
Triple: [Mazandaran Province, hasCity, Neka]
Generated description
Neka is a city in northern Iran known for its location near the Caspian Sea and its role as an industrial and agricultural center in Mazandaran Province.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Neka
Target entity description: Neka is a city in northern Iran known for its location near the Caspian Sea and its role as an industrial and agricultural center in Mazandaran Province.
  • A. Nese
    Nese is an endangered Oceanic language spoken by a small community on the island of Malakula in Vanuatu.
  • B. Neyo
    Ne-Yo is an American R&B singer, songwriter, and record producer known for hits like "So Sick" and "Closer" and for writing songs for numerous major artists.
  • C. Némi
    Némi is an Oceanic language spoken by a small indigenous community in New Caledonia.
  • D. Nele
    Nele is a Kannada novel by acclaimed Indian writer S. L. Bhyrappa, known for its philosophical depth and exploration of human values.
  • E. Nane
    Nane is a Swedish lawyer and artist best known as the widow of former United Nations Secretary-General Kofi Annan.
  • F. None of above. chosen

Provenance (5 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_69ca82bfeb6481909d07b91b5cf69f59 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb45537d248190a0e998b6d336e6e1 completed March 31, 2026, 3:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69ccbf21ab2c8190af23b4a3a4bdb543 completed April 1, 2026, 6:45 a.m.
NEDg Description generation batch_69ccc24c5684819093a4f58616122675 completed April 1, 2026, 6:59 a.m.
NED2 Entity disambiguation (via description) batch_69ccc38e85bc8190b0f4b2435a385f47 completed April 1, 2026, 7:04 a.m.
Created at: March 30, 2026, 5:38 p.m.