Triple

T9122010
Position Surface form Disambiguated ID Type / Status
Subject R103 E218875 entity
Predicate connects P390 FINISHED
Object Mooi River E784701 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: Mooi River | Statement: [R103, connects, Mooi River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mooi River
Context triple: [R103, connects, Mooi River]
  • A. Mooi River chosen
    Mooi River is a small town in KwaZulu-Natal, South Africa, known for its agricultural surroundings and role as a stopover point along major transport routes.
  • B. Grobbelaars River
    Grobbelaars River is a watercourse in South Africa’s Western Cape that flows through the town of Oudtshoorn in the semi-arid Little Karoo region.
  • C. Pienaars River
    Pienaars River is a tributary watercourse in South Africa that feeds into the Crocodile River within the Limpopo River basin.
  • D. Vaalharts River
    The Vaalharts River is a smaller watercourse in South Africa that feeds into the Vaal River and supports the surrounding agricultural region.
  • E. Touw River
    The Touw River is a scenic river in South Africa’s Western Cape that flows through the Wilderness area and its surrounding lakes before reaching the Indian Ocean.
  • 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_69ca83dddd548190983b96c664f7f367 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cca8b46dac8190bde88205c85f596a completed April 1, 2026, 5:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0f36115c48190bdf0fe6c2eda1252 completed April 4, 2026, 11:17 a.m.
Created at: March 30, 2026, 7:17 p.m.