Triple

T15683379
Position Surface form Disambiguated ID Type / Status
Subject Mandara Hut E377634 entity
Predicate route P5619 FINISHED
Object Marangu Route E76523 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: Marangu Route | Statement: [Mandara Hut, route, Marangu Route]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marangu Route
Context triple: [Mandara Hut, route, Marangu Route]
  • A. Marangu Route chosen
    Marangu Route is a popular and relatively easier trekking path up Mount Kilimanjaro, known for its hut accommodations and gradual slopes.
  • B. Marangu Gate
    Marangu Gate is the main entrance to Kilimanjaro National Park used by climbers beginning the popular Marangu Route up Mount Kilimanjaro in Tanzania.
  • C. Lemosho Route
    Lemosho Route is a popular, scenic multi-day trekking path used by climbers to ascend Mount Kilimanjaro from its western side.
  • D. Rongai Route
    Rongai Route is one of the main trekking paths used to ascend Mount Kilimanjaro, known for its quieter northern approach and relatively gentle, scenic climb.
  • E. Machame Route
    Machame Route is one of the most popular and scenic trekking paths used by climbers to ascend Mount Kilimanjaro in Tanzania.
  • 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_69d85cd2e28481909d4e975bee20872f completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04f31b5b881908e46ecd9fc6048ab completed April 16, 2026, 2:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff6ee4c8688190ae2fefb56171161a completed May 9, 2026, 5:29 p.m.
Created at: April 10, 2026, 4:17 a.m.