Triple

T23348547
Position Surface form Disambiguated ID Type / Status
Subject Mungo E591937 entity
Predicate relatedTo P37 FINISHED
Object Duala NE NERFINISHED

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: Duala | Statement: [Mungo, relatedTo, Duala]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Duala
Context triple: [Mungo, relatedTo, Duala]
  • A. Duala chosen
    Duala is a Bantu language spoken primarily by the Duala people in the coastal regions of Cameroon, especially around the city of Douala.
  • B. Dvoynik
    Dvoynik is the original Russian title of Fyodor Dostoevsky’s novella "The Double," a psychological work about a government clerk who encounters his uncanny doppelgänger.
  • C. Duaenhor
    Duaenhor was an ancient Egyptian prince of the 4th Dynasty, likely a grandson of Pharaoh Khufu and a member of the royal family buried at Giza.
  • D. Dua
    Dua is the first name of Dua Lipa, a British-Albanian pop singer and songwriter known for hits like "New Rules" and "Levitating."
  • E. Duellona
    Duellona is an epithet of the Roman war goddess Bellona, emphasizing her role as a fierce deity of battle and conflict.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e25d20e3d08190bcede87673cafb25 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f199cb2a3c8190a5c0c8d8735256c7 completed April 29, 2026, 5:40 a.m.
Created at: April 17, 2026, 5:19 p.m.