Triple

T8390853
Position Surface form Disambiguated ID Type / Status
Subject Luwians E197938 entity
Predicate associatedWith P37 FINISHED
Object Tarhuntassa E195341 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: Tarhuntassa | Statement: [Luwians, associatedWith, Tarhuntassa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tarhuntassa
Context triple: [Luwians, associatedWith, Tarhuntassa]
  • A. Tarhuntassa chosen
    Tarhuntassa was an important Late Bronze Age city in southern Anatolia that briefly served as a secondary capital of the Hittite Empire.
  • B. Tarasicodissa
    Tarasicodissa was the original name of the Eastern Roman emperor Zeno, who ruled from 474 to 491 AD.
  • C. Tabasaran
    Tabasaran is a Northeast Caucasian language spoken primarily by the Tabasaran people in southern Dagestan, Russia.
  • D. Tainaste
    Tainaste is a small settlement located in the Middle Atlas region of Morocco, near the mountain Jbel Bou Naceur.
  • E. Taravai
    Taravai is one of the inhabited islands of the Gambier Islands archipelago in French Polynesia, known for its remote location and traditional Polynesian character.
  • 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_69ca82f749388190bffbea6dfb509016 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb810c5c5c81908e124c64911c4e6c completed March 31, 2026, 8:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69cde84d6f3c8190ba12905ba5900087 completed April 2, 2026, 3:53 a.m.
Created at: March 30, 2026, 6:03 p.m.