Triple

T15338814
Position Surface form Disambiguated ID Type / Status
Subject Drau E366735 entity
Predicate hasMajorTributary P415 FINISHED
Object Dravinja E365639 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: Dravinja | Statement: [Drau, hasMajorTributary, Dravinja]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dravinja
Context triple: [Drau, hasMajorTributary, Dravinja]
  • A. Dravinja chosen
    Dravinja is a river in northeastern Slovenia that flows through the Dravinja Valley before joining the Drava River.
  • B. Drino River
    The Drino River is a river in southern Albania that flows through Gjirokastër County and is a tributary of the Vjosë River.
  • C. Vodnjese
    Vodnjese is a local dialect of the Istriot language traditionally spoken in and around the town of Vodnjan in Istria.
  • D. Salaca River
    The Salaca River is a river in northern Latvia that flows from Lake Burtnieks to the Gulf of Riga, known for its scenic sandstone cliffs and role in the region’s natural and cultural heritage.
  • E. Driva River
    Driva River is a major river in central Norway that flows through the Oppdal region, known for its scenic valleys and salmon fishing.
  • 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_69d85a1355608190a6673ddb67231d54 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e12eb7c8190944a260aa1aa9156 completed April 16, 2026, 1:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff219635b08190a19dcaeb72240379 completed May 9, 2026, 11:59 a.m.
Created at: April 10, 2026, 3:17 a.m.