Triple

T7699471
Position Surface form Disambiguated ID Type / Status
Subject Mysia E174451 entity
Predicate hasCity P316 FINISHED
Object Zeleia
Zeleia was an ancient city in the region of Mysia in northwestern Asia Minor, known from classical Greek and Roman historical and geographical sources.
 E682880 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: Zeleia | Statement: [Mysia, hasCity, Zeleia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Zeleia
Context triple: [Mysia, hasCity, Zeleia]
  • A. Anala
    Anala is a lesser-known name or aspect of Agni, the Vedic god of fire in Hindu mythology.
  • B. Adalinda
    Adalinda was a medieval noblewoman known primarily as the wife of William I, Duke of Aquitaine.
  • C. Clorinda
    Clorinda is a border city in northeastern Argentina’s Formosa Province, located opposite Asunción, Paraguay, and serving as an important regional commercial and transport hub.
  • D. Luciana
    Luciana is a feminine given name of Latin origin, commonly used in Spanish- and Portuguese-speaking countries.
  • E. Zarité Sedella
    Zarité Sedella is the enslaved Haitian woman of mixed African and Indigenous descent whose life, resilience, and quest for freedom drive the narrative of Isabel Allende’s historical novel "Island Beneath the Sea."
  • 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: Zeleia
Triple: [Mysia, hasCity, Zeleia]
Generated description
Zeleia was an ancient city in the region of Mysia in northwestern Asia Minor, known from classical Greek and Roman historical and geographical sources.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Zeleia
Target entity description: Zeleia was an ancient city in the region of Mysia in northwestern Asia Minor, known from classical Greek and Roman historical and geographical sources.
  • A. Anala
    Anala is a lesser-known name or aspect of Agni, the Vedic god of fire in Hindu mythology.
  • B. Adalinda
    Adalinda was a medieval noblewoman known primarily as the wife of William I, Duke of Aquitaine.
  • C. Clorinda
    Clorinda is a border city in northeastern Argentina’s Formosa Province, located opposite Asunción, Paraguay, and serving as an important regional commercial and transport hub.
  • D. Luciana
    Luciana is a feminine given name of Latin origin, commonly used in Spanish- and Portuguese-speaking countries.
  • E. Zarité Sedella
    Zarité Sedella is the enslaved Haitian woman of mixed African and Indigenous descent whose life, resilience, and quest for freedom drive the narrative of Isabel Allende’s historical novel "Island Beneath the Sea."
  • 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_69c6995a72cc8190998e56daa6f8e453 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c7026ba7b48190a18f1c1cbbf1b944 completed March 27, 2026, 10:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8acb3ac4481909acafe50b9507aaa completed March 29, 2026, 4:38 a.m.
NEDg Description generation batch_69c8adeb3948819087404b0d7d7e619e completed March 29, 2026, 4:43 a.m.
NED2 Entity disambiguation (via description) batch_69c8aedede388190b8eb79cea223c31c completed March 29, 2026, 4:47 a.m.
Created at: March 27, 2026, 4:03 p.m.