Triple

T8041985
Position Surface form Disambiguated ID Type / Status
Subject Mālaqa E187461 entity
Predicate preIslamicName P80710 FINISHED
Object Malaca E187460 NE FINISHED

How this triple was built (3 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: Malaca | Statement: [Mālaqa, preIslamicName, Malaca]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Malaca
Context triple: [Mālaqa, preIslamicName, Malaca]
  • A. Malaka chosen
    Malaka is the ancient Phoenician and later Roman name for the city now known as Málaga in southern Spain.
  • B. Malacca
    Malacca is a historic Malaysian state on the southwest coast of the Malay Peninsula, renowned for its rich multicultural heritage and its former role as a major trading port.
  • C. Macassar
    Macassar is the former name of Makassar, a major port city on the island of Sulawesi in Indonesia known historically as an important center of trade and maritime power.
  • D. Malabo Lopelo Melaka
    Malabo Lopelo Melaka was a historical Bubi leader from Bioko Island whose name was later given to Equatorial Guinea’s capital city, Malabo.
  • E. Labuan
    Labuan is a coastal town in Banten, western Java, Indonesia, known as a gateway to nearby natural attractions and marine tourism areas.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: preIslamicName
Context triple: [Mālaqa, preIslamicName, Malaca]
  • A. preIslamicFigure
    Indicates that the subject is a notable person or character who lived or is traditionally placed in the period before the advent of Islam.
  • B. preRomanName
    Indicates the name by which an entity (such as a place or people) was known before the Roman period or prior to receiving a Roman-era name.
  • C. preIslamicReligion
    Indicates that an entity practiced, adhered to, or was associated with a religious belief system that existed before the advent or spread of Islam.
  • D. preIslamicRulerOf
    Indicates that one entity served as the ruler of another entity (such as a territory or people) during the period before the advent of Islam.
  • E. preIslamicPresence
    Indicates the existence or activity of someone or something in a place or context during the period before the advent of Islam.
  • F. None of above. chosen

Provenance (5 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_69ca82b00cb48190b59a300f70e97bd7 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3f1e98508190a29a7bb5055f8ba0 completed March 31, 2026, 3:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc93c407cc81908029bfdd5a0393f1 completed April 1, 2026, 3:40 a.m.
PD Predicate disambiguation batch_69cb049688208190b32088bd2c5930bc completed March 30, 2026, 11:17 p.m.
PDg Predicate description generation batch_69cb14bcbbc0819094a98e7ffffb7a40 completed March 31, 2026, 12:26 a.m.
Created at: March 30, 2026, 5:23 p.m.