Triple

T19570535
Position Surface form Disambiguated ID Type / Status
Subject Brynaman E489700 entity
Predicate crossedBy P416 FINISHED
Object River Amman 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: River Amman | Statement: [Brynaman, crossedBy, River Amman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: River Amman
Context triple: [Brynaman, crossedBy, River Amman]
  • A. River Amman chosen
    River Amman is a river in south Wales that flows through the town of Ammanford and the surrounding Amman Valley before joining the River Loughor.
  • B. Yarmouk River
    The Yarmouk River is a major river in the Levant that forms part of the border between Jordan, Syria, and Israel before joining the Jordan River.
  • C. Aley River
    The Aley River is a waterway in southwestern Siberia, Russia, that flows through the Altai Krai region and supports towns such as Rubtsovsk along its banks.
  • D. Zarqa River
    The Zarqa River is a major river in Jordan that flows through the country’s highlands and urban areas before joining the Jordan River.
  • E. Ayad River
    The Ayad River is a watercourse in Rajasthan, India, that feeds and drains Lake Pichola and plays a key role in the hydrology of the Udaipur region.
  • 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_69d8e8dd9374819098e36349b3211663 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6402043588190a99f5a55c5dcd8a6 completed April 20, 2026, 3:02 p.m.
Created at: April 10, 2026, 1:42 p.m.