Triple

T1781202
Position Surface form Disambiguated ID Type / Status
Subject Lydian E39294 entity
Predicate closelyRelatedTo P37 FINISHED
Object Hittite E39433 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: Hittite | Statement: [Lydian, closelyRelatedTo, Hittite]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hittite
Context triple: [Lydian, closelyRelatedTo, Hittite]
  • A. Hittite (Nesite) chosen
    Hittite (Nesite) is an extinct Indo-European language of ancient Anatolia, known from cuneiform texts and often regarded as the earliest attested Indo-European language.
  • B. Hurrian
    Hurrian was an ancient Near Eastern language spoken by the Hurrian people, influential in the linguistic and cultural milieu of Bronze Age Anatolia and Mesopotamia.
  • C. Luwians
    The Luwians were an ancient Indo-European people of Anatolia closely related to the Hittites, known for their own language, hieroglyphic script, and significant role in the Late Bronze Age civilizations of the region.
  • D. Lydian
    Lydian is an extinct Indo-European language once spoken in the ancient kingdom of Lydia in western Anatolia.
  • E. Anatolian languages
    Anatolian languages are an extinct branch of the Indo-European language family once spoken in ancient Anatolia, including languages such as Hittite and Luwian.
  • 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_69a88630519c8190a17addd83c4a3ef4 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa64e22d6881909ba6ec120b320918 completed March 6, 2026, 5:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69adfb9c69488190abcbbf796176fca5 completed March 8, 2026, 10:43 p.m.
Created at: March 4, 2026, 7:31 p.m.