Triple

T8266604
Position Surface form Disambiguated ID Type / Status
Subject Luwic E193316 entity
Predicate includes P1393 FINISHED
Object Milyan E37898 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: Milyan | Statement: [Luwic, includes, Milyan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Milyan
Context triple: [Luwic, includes, Milyan]
  • A. Milyan chosen
    Milyan is an extinct Anatolian Indo-European language once spoken in southwestern Asia Minor, known primarily from a small corpus of inscriptions.
  • B. Milies
    Milies is a traditional mountain village in Greece known for its stone architecture, rich cultural heritage, and scenic location on the slopes of Mount Pelion.
  • C. Mille
    Mille is a French surname most notably borne by individuals such as Stéphane Mille.
  • D. Mino
    Mino were an elite all-female military regiment of the Kingdom of Dahomey, renowned for their discipline, bravery, and significant role in the kingdom’s warfare.
  • E. Manyika
    Manyika is a major dialect of the Shona language spoken primarily in eastern Zimbabwe and adjacent areas of Mozambique.
  • 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_69ca82e081d48190986beaa51f498ab9 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb794e6880819084dff5df42332835 completed March 31, 2026, 7:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd6827e44c81909be6e426ab9226c7 completed April 1, 2026, 6:47 p.m.
Created at: March 30, 2026, 5:50 p.m.