Triple

T8266130
Position Surface form Disambiguated ID Type / Status
Subject Mursili II E193305 entity
Predicate mother P120 FINISHED
Object Henti E722158 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: Henti | Statement: [Mursili II, mother, Henti]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Henti
Context triple: [Mursili II, mother, Henti]
  • A. Henti chosen
    Henti was a queen of the Hittite Empire, known primarily as the wife of the powerful 14th-century BCE king Suppiluliuma I.
  • B. Halt
    Halt is the surname of Karl Ritter von Halt, a notable German sports official and International Olympic Committee member in the early to mid-20th century.
  • C. Ponto de Parada
    Ponto de Parada is a neighborhood in the city of Recife, Brazil, known primarily as a residential area within the metropolitan region.
  • D. Shikasta
    Shikasta is a 1979 science fiction novel by Doris Lessing that inaugurates her Canopus in Argos series, blending cosmic history with political and spiritual allegory.
  • E. Toinette
    Toinette is the sharp-witted, outspoken maid in Molière’s comedy "Le Malade imaginaire," known for her clever schemes and satirical commentary on her hypochondriac master.
  • 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.