Triple

T4018416
Position Surface form Disambiguated ID Type / Status
Subject Bandar Lampung E91220 entity
Predicate connectsIslands P53472 FINISHED
Object Sumatra E14825 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: Sumatra | Statement: [Bandar Lampung, connectsIslands, Sumatra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sumatra
Context triple: [Bandar Lampung, connectsIslands, Sumatra]
  • A. Sumatra chosen
    Sumatra is a large Indonesian island in western Indonesia known for its rich biodiversity, active volcanoes, and significant role in regional trade and history.
  • B. North Sumatra
    North Sumatra is a populous province on the Indonesian island of Sumatra, known for its diverse cultures, Lake Toba, and the city of Medan as its capital.
  • C. Kalimantan
    Kalimantan is the Indonesian portion of the island of Borneo, known for its vast rainforests, rich biodiversity, and significant natural resources.
  • D. Isle of Java
    Isle of Java is a coffee-focused quick-service location at Disney’s Discovery Island, known for serving beverages and light refreshments to park guests.
  • E. Greater Sunda Islands
    The Greater Sunda Islands are a major group of large islands in maritime Southeast Asia, including Java, Sumatra, Borneo, and Sulawesi, known for their rich biodiversity and dense human populations.
  • 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: connectsIslands
Context triple: [Bandar Lampung, connectsIslands, Sumatra]
  • A. connectsRegions
    Indicates a relationship where one entity links or joins two or more distinct regions, enabling passage, interaction, or continuity between them.
  • B. numberOfArtificialIslands
    Indicates the quantitative count of artificial islands associated with or contained within a given entity.
  • C. numberOfIslands
    Indicates the total count of distinct, separate landmasses (islands) present within a given area or context.
  • D. connectsTo
    Indicates a relationship where one entity is linked or joined to another, allowing interaction, communication, or transfer between them.
  • E. connectsLandform
    Indicates a relationship where one landform serves as a physical link or passage between two or more other landforms.
  • 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_69aed9618b04819081750d979d2af098 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefaa984948190a252eaeb9dbae454 completed March 9, 2026, 4:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69b56b39f55c819099e5ce90137de570 completed March 14, 2026, 2:05 p.m.
PD Predicate disambiguation batch_69aef8fc78ec819092d4dab88d85a141 completed March 9, 2026, 4:44 p.m.
PDg Predicate description generation batch_69aefa815f2c8190818c9ffd9d1bf478 completed March 9, 2026, 4:51 p.m.
Created at: March 9, 2026, 3:35 p.m.