Triple

T16774230
Position Surface form Disambiguated ID Type / Status
Subject siglos E407680 entity
Predicate complements P162 FINISHED
Object daric E83626 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: daric | Statement: [siglos, complements, daric]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: daric
Context triple: [siglos, complements, daric]
  • A. daric chosen
    The daric was a high-purity gold coin of the Achaemenid Persian Empire, widely used across its territories and influential in ancient Near Eastern and Greek economies.
  • B. Daric
    The Daric was a high-purity gold coin of the Achaemenid Persian Empire, widely used across its territories and emblematic of its economic power.
  • C. Dar
    Dar is a character from the 1935 French film "Princesse Tam-Tam," which starred Josephine Baker.
  • D. Dar
    Dar is the warrior protagonist and titular Beastmaster of the Beastmaster fantasy franchise, known for his ability to telepathically communicate with and command animals.
  • E. DRAC
    DRAC is the French acronym for the Regional Directorates of Cultural Affairs, which are state administrations responsible for implementing national cultural policy at the regional level in France.
  • 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_69d8839270588190886720d9519bbf8f completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b038d0608190be15c758427bb664 completed April 18, 2026, 4:24 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00b28592c08190855a7fa5b0a350f5 completed May 10, 2026, 4:29 p.m.
Created at: April 10, 2026, 5:22 a.m.