Triple

T4527216
Position Surface form Disambiguated ID Type / Status
Subject Logudoro E106207 entity
Predicate contains P35 FINISHED
Object Sedini E423878 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: Sedini | Statement: [Logudoro, contains, Sedini]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sedini
Context triple: [Logudoro, contains, Sedini]
  • A. Sedini chosen
    Sedini is a small historic town in northern Sardinia, Italy, known for its distinctive rock-carved dwellings and traditional rural character.
  • B. Caudini
    The Caudini were an ancient Italic people forming one of the principal tribes of the Samnite confederation in southern Italy.
  • C. Arrifes
    Arrifes is a civil parish in the municipality of Ponta Delgada on São Miguel Island in Portugal’s Azores archipelago.
  • D. Odzaci
    Odžaci is a town and municipality in the Bačka region of northern Serbia, known for its agricultural production and location near the Danube River.
  • E. Gonda
    Gonda is a city in the Indian state of Uttar Pradesh, known for its agricultural economy and proximity to the Ghaghara River.
  • 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_69bd43f3d6e08190a91824f833d51bbe completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd577737848190ad509c8bb8e57ec0 completed March 20, 2026, 2:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69bda4577d0c8190a88cdf4523446329 completed March 20, 2026, 7:47 p.m.
Created at: March 20, 2026, 1:03 p.m.