Triple

T5444059
Position Surface form Disambiguated ID Type / Status
Subject Ecbatana E122204 entity
Predicate greekName P3659 FINISHED
Object Ekbátana
Ekbátana is the ancient Greek name for the city of Ecbatana, the historic capital of the Median Empire in what is now western Iran.
E520297 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: Ekbátana | Statement: [Ecbatana, greekName, Ekbátana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ekbátana
Context triple: [Ecbatana, greekName, Ekbátana]
  • A. Kadmat
    Kadmat is a coral island in India’s Lakshadweep archipelago, known for its white-sand beaches, clear lagoons, and vibrant marine life that make it a popular destination for snorkeling and diving.
  • B. Kartasura
    Kartasura is a historic Javanese town in Central Java, Indonesia, known for having been an important royal center of the Mataram Sultanate before the court moved to Surakarta.
  • C. Kalkan
    Kalkan is a picturesque seaside town on Turkey’s Mediterranean coast, known for its historic architecture, steep cobbled streets, and upscale tourism.
  • D. Candaba
    Candaba is a municipality in the Philippine province of Pampanga known for its vast wetlands and rich bird-watching sites.
  • E. Samalkha
    Samalkha is a town in the northern Indian state of Haryana, known for its industrial activity and location along major transport routes.
  • 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: Ekbátana
Triple: [Ecbatana, greekName, Ekbátana]
Generated description
Ekbátana is the ancient Greek name for the city of Ecbatana, the historic capital of the Median Empire in what is now western Iran.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ekbátana
Target entity description: Ekbátana is the ancient Greek name for the city of Ecbatana, the historic capital of the Median Empire in what is now western Iran.
  • A. Kadmat
    Kadmat is a coral island in India’s Lakshadweep archipelago, known for its white-sand beaches, clear lagoons, and vibrant marine life that make it a popular destination for snorkeling and diving.
  • B. Kartasura
    Kartasura is a historic Javanese town in Central Java, Indonesia, known for having been an important royal center of the Mataram Sultanate before the court moved to Surakarta.
  • C. Kalkan
    Kalkan is a picturesque seaside town on Turkey’s Mediterranean coast, known for its historic architecture, steep cobbled streets, and upscale tourism.
  • D. Candaba
    Candaba is a municipality in the Philippine province of Pampanga known for its vast wetlands and rich bird-watching sites.
  • E. Samalkha
    Samalkha is a town in the northern Indian state of Haryana, known for its industrial activity and location along major transport routes.
  • 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_69bd4640f52c81909e653ec361f66d76 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd91ccdd648190940c04781c4222ec completed March 20, 2026, 6:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf4132bcf08190af2ca506a40fb26e completed March 22, 2026, 1:09 a.m.
NEDg Description generation batch_69bf4207393c819089b4fc6691a2d076 completed March 22, 2026, 1:12 a.m.
NED2 Entity disambiguation (via description) batch_69bf427e2bd08190b7664922d26e16d2 completed March 22, 2026, 1:14 a.m.
Created at: March 20, 2026, 2:07 p.m.