Triple

T16692134
Position Surface form Disambiguated ID Type / Status
Subject Merak E405619 entity
Predicate connectsTo P845 FINISHED
Object Bakauheni E707366 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: Bakauheni | Statement: [Merak, connectsTo, Bakauheni]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bakauheni
Context triple: [Merak, connectsTo, Bakauheni]
  • A. Bakauheni chosen
    Bakauheni is a major port town in southern Sumatra, Indonesia, serving as a key ferry gateway between Sumatra and Java.
  • B. Bandar Lengeh
    Bandar Lengeh is a coastal city and important maritime port on the Persian Gulf in southern Iran’s Hormozgan Province.
  • C. Pelabuhan Ratu
    Pelabuhan Ratu is a coastal town and bay in West Java, Indonesia, known for its scenic beaches, strong surf, and local fishing culture.
  • D. Port of Ambon
    The Port of Ambon is a key maritime hub in eastern Indonesia, serving as a major gateway for regional trade, passenger transport, and fisheries around Ambon Island and the Maluku archipelago.
  • E. Port of Surabaya
    The Port of Surabaya is a major Indonesian seaport on the northern coast of Java that serves as a key commercial and shipping hub in the Asia-Pacific region.
  • 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_69d8838c28748190b3f5967c743940ab completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e37eaacb948190954231c9e97a4adf completed April 18, 2026, 12:52 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0091984dcc8190b0b20d2e57bc3a11 completed May 10, 2026, 2:09 p.m.
Created at: April 10, 2026, 5:19 a.m.