Triple

T1351079
Position Surface form Disambiguated ID Type / Status
Subject Malang E28882 entity
Predicate locatedNear P294 FINISHED
Object Mount Bromo E22411 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: Mount Bromo | Statement: [Malang, locatedNear, Mount Bromo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mount Bromo
Context triple: [Malang, locatedNear, Mount Bromo]
  • A. Mount Bromo chosen
    Mount Bromo is an active and highly popular volcano in East Java, Indonesia, renowned for its dramatic crater landscape and sunrise views within the Tengger caldera.
  • B. Mount Rinjani
    Mount Rinjani is an active stratovolcano on the island of Lombok known for its large caldera lake, challenging trekking routes, and significant cultural and geological importance.
  • C. Mount Semeru
    Mount Semeru is the highest and one of the most active volcanoes on the Indonesian island of Java, renowned for its frequent eruptions and prominent conical peak.
  • D. Mount Batur
    Mount Batur is an active stratovolcano in northeastern Bali, Indonesia, known for its scenic caldera lake and popular sunrise treks.
  • E. Tangkuban Perahu
    Tangkuban Perahu is a popular stratovolcano in West Java, Indonesia, known for its distinctive boat-like shape and easily accessible craters.
  • 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_69a498571d248190a0ac9eb02d97097f completed March 1, 2026, 7:49 p.m.
NER Named-entity recognition batch_69a4c26b1b4881908ae4b1b2c9b268a0 completed March 1, 2026, 10:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69acce6a1dd48190b17ac5a7cf3ab933 completed March 8, 2026, 1:18 a.m.
Created at: March 1, 2026, 7:56 p.m.