Triple

T20777795
Position Surface form Disambiguated ID Type / Status
Subject siege of Abidjan E511398 entity
Predicate location P40 FINISHED
Object Plateau E339615 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: Plateau | Statement: [siege of Abidjan, location, Plateau]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Plateau
Context triple: [siege of Abidjan, location, Plateau]
  • A. Plateau chosen
    Plateau is the central business district of Abidjan, known for its concentration of government institutions, corporate headquarters, and modern high-rise buildings.
  • B. Plateau
    The Plateau is a cultural and geographic region of North America characterized by intermontane river valleys and uplands, traditionally inhabited by Indigenous peoples such as the Spokan.
  • C. The Plateau
    The Plateau is a trendy, artsy neighborhood in Montreal known for its colorful row houses, vibrant street art, and lively café and nightlife scene.
  • D. PLATEAU
    PLATEAU is a state in central Nigeria known for its diverse ethnic groups, cool climate, and the city of Jos as its capital.
  • E. Roztocze plateau
    The Roztocze plateau is a picturesque upland region in southeastern Poland known for its rolling hills, forests, and protected natural landscapes.
  • 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_69e0b4cac7a48190a715cb3d545df2b4 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c26d34bc81908bb22087d434322d completed April 21, 2026, 12:18 a.m.
NED1 Entity disambiguation (via context triple) batch_6a08ef97b6fc819084beba382b05b813 completed May 16, 2026, 10:28 p.m.
Created at: April 16, 2026, 12:37 p.m.