Triple

T11119597
Position Surface form Disambiguated ID Type / Status
Subject Mangalyaan E262980 entity
Predicate spaceAgencyHeadquarters P97651 FINISHED
Object Bengaluru E12663 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: Bengaluru | Statement: [Mangalyaan, spaceAgencyHeadquarters, Bengaluru]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bengaluru
Context triple: [Mangalyaan, spaceAgencyHeadquarters, Bengaluru]
  • A. Bengaluru chosen
    Bengaluru is a major Indian metropolis known as the country’s leading technology and innovation hub, often called the “Silicon Valley of India.”
  • B. Mambai
    Mambai is an Austronesian language spoken primarily in East Timor, where it is one of the country’s major indigenous languages.
  • C. Hyderabad
    Hyderabad is a major city in southern India known for its historic Charminar monument, rich Hyderabadi cuisine, and growing technology industry.
  • D. Hyderabad
    Hyderabad is a major city in the Sindh province of Pakistan, known for its historical significance, vibrant culture, and role as an important commercial and industrial center.
  • E. Mysuru
    Mysuru is a historic city in the southern Indian state of Karnataka, renowned for its royal heritage, palaces, and cultural festivals such as Dasara.
  • 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: spaceAgencyHeadquarters
Context triple: [Mangalyaan, spaceAgencyHeadquarters, Bengaluru]
  • A. spaceAgency
    Indicates that one entity is a space agency that operates, manages, or oversees space-related missions, programs, or activities on behalf of the other entity.
  • B. spaceLaunchDestination
    Indicates the target location or body in space toward which a space launch is directed.
  • C. largestSpaceportIn
    Indicates that one entity is the largest spaceport located within the geographic or administrative area represented by the other entity.
  • D. hostSpaceAgency
    Indicates that one entity serves as the space agency that organizes, manages, or officially represents space-related activities for another entity (such as a mission, event, or facility).
  • E. spaceportLocation
    Indicates the place where a spaceport is situated or hosted.
  • 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_69d6aa9b46cc8190b19f9f0cc45bf322 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d79af7b72c8190a19dbcbb3a69fb5b completed April 9, 2026, 12:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69e42d4f9518819091f7e02ad5f63ab3 completed April 19, 2026, 1:18 a.m.
PD Predicate disambiguation batch_69d7441efe948190ae4ab020121e169d completed April 9, 2026, 6:15 a.m.
PDg Predicate description generation batch_69d75112eb1c8190ba1dd51e42e8a7e8 completed April 9, 2026, 7:11 a.m.
Created at: April 8, 2026, 9:28 p.m.