Triple

T4796584
Position Surface form Disambiguated ID Type / Status
Subject Aeolis E106726 entity
Predicate hasCity P316 FINISHED
Object Aigai
Aigai was an ancient Greek city of Aeolis in western Asia Minor, known as one of the Aeolian dodecapolis.
 E471483 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: Aigai | Statement: [Aeolis, hasCity, Aigai]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Aigai
Context triple: [Aeolis, hasCity, Aigai]
  • A. Aigai
    Aigai was the ancient capital of the kingdom of Macedon, historically significant as the royal seat and burial place of its kings before the rise of Pella.
  • B. Ageo
    Ageo is a city in Japan known as a residential and industrial hub within the Greater Tokyo metropolitan area.
  • C. Ayizan
    Ayizan is a prominent Haitian Vodou spirit revered as the patron of marketplaces, initiation rites, and sacred knowledge, especially associated with commerce and spiritual purity.
  • D. Shimaore
    Shimaore is a Bantu language closely related to Comorian, widely spoken by the local population of Mayotte in the Indian Ocean.
  • E. Taihoku
    Taihoku was the Japanese colonial-era name for Taipei, which served as the administrative and political center of Taiwan under Japanese rule.
  • 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: Aigai
Triple: [Aeolis, hasCity, Aigai]
Generated description
Aigai was an ancient Greek city of Aeolis in western Asia Minor, known as one of the Aeolian dodecapolis.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Aigai
Target entity description: Aigai was an ancient Greek city of Aeolis in western Asia Minor, known as one of the Aeolian dodecapolis.
  • A. Aigai
    Aigai was the ancient capital of the kingdom of Macedon, historically significant as the royal seat and burial place of its kings before the rise of Pella.
  • B. Ageo
    Ageo is a city in Japan known as a residential and industrial hub within the Greater Tokyo metropolitan area.
  • C. Ayizan
    Ayizan is a prominent Haitian Vodou spirit revered as the patron of marketplaces, initiation rites, and sacred knowledge, especially associated with commerce and spiritual purity.
  • D. Shimaore
    Shimaore is a Bantu language closely related to Comorian, widely spoken by the local population of Mayotte in the Indian Ocean.
  • E. Taihoku
    Taihoku was the Japanese colonial-era name for Taipei, which served as the administrative and political center of Taiwan under Japanese rule.
  • 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_69bd43f591c881909e5a532388b0f3f3 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd660b05ec8190971f43350f02fed4 completed March 20, 2026, 3:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69be4d9a76c08190bd19fcef378cd640 completed March 21, 2026, 7:49 a.m.
NEDg Description generation batch_69be4e764b60819097aace8e7321dc0c completed March 21, 2026, 7:53 a.m.
NED2 Entity disambiguation (via description) batch_69be4ef501e081908a75547e9bb52c0c completed March 21, 2026, 7:55 a.m.
Created at: March 20, 2026, 1:22 p.m.