Triple

T3461648
Position Surface form Disambiguated ID Type / Status
Subject Lemnos E73038 entity
Predicate hasSettlement P1068 FINISHED
Object Kornos E293693 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: Kornos | Statement: [Lemnos, hasSettlement, Kornos]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kornos
Context triple: [Lemnos, hasSettlement, Kornos]
  • A. Kameçvara
    Kameçvara was a prominent king of the medieval Javanese Kediri Kingdom, remembered for his prosperous reign and association with the classic romance tale of Panji.
  • B. Krakhuna
    Krakhuna is a Georgian white grape variety from the Imereti region, known for producing aromatic, full-bodied wines with pronounced acidity.
  • C. Koropi chosen
    Koropi is a town in the Athens metropolitan area of Greece, known as the seat of the municipality of Kropia and a local hub in the Mesogeia plain.
  • D. Kohistanis
    Kohistanis are an Indo-Aryan ethnic group primarily inhabiting the mountainous Kohistan region of northern Pakistan, known for their distinct languages and traditional highland culture.
  • E. Oreshek
    Oreshek is the historic Russian fortress on Lake Ladoga that later gave rise to the town of Shlisselburg.
  • 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_69ad85b224d481908ff8be51338d24ff completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adbae745e081909007cd3a664c57f3 completed March 8, 2026, 6:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69b3611ff950819081b49f5c75aa6e4d completed March 13, 2026, 12:58 a.m.
Created at: March 8, 2026, 3:17 p.m.