Triple

T8773142
Position Surface form Disambiguated ID Type / Status
Subject Kalaripayattu E208512 entity
Predicate weaponUsed P706 FINISHED
Object urumi
The urumi is a traditional South Indian flexible, whip-like sword known for its multiple long, ribbon-like blades and demanding, acrobatic fighting techniques.
 E757664 NE FINISHED

How this triple was built (4 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: urumi | Statement: [Kalaripayattu, weaponUsed, urumi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: urumi
Context triple: [Kalaripayattu, weaponUsed, urumi]
  • A. Ushishiru
    Ushishiru is the Japanese name for Ushishir, a volcanic island in Russia’s Kuril Islands chain known for its caldera and geothermal activity.
  • B. URU
    URU is the FIFA country code used to represent the Uruguay national football team in international competitions and rankings.
  • C. URMO
    URMO is the ICAO airport code for Beslan Airport, which serves the city of Vladikavkaz in North Ossetia–Alania, Russia.
  • D. Rumuokurusi
    Rumuokurusi is a prominent urban community in Obio-Akpor, Rivers State, Nigeria, known for its commercial activity and strategic location within the Port Harcourt metropolitan area.
  • E. Komuro
    Komuro is the married surname of Japan’s former Princess Mako, adopted after her marriage to commoner Kei Komuro.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: urumi
Triple: [Kalaripayattu, weaponUsed, urumi]
Generated description
The urumi is a traditional South Indian flexible, whip-like sword known for its multiple long, ribbon-like blades and demanding, acrobatic fighting techniques.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: urumi
Target entity description: The urumi is a traditional South Indian flexible, whip-like sword known for its multiple long, ribbon-like blades and demanding, acrobatic fighting techniques.
  • A. Ushishiru
    Ushishiru is the Japanese name for Ushishir, a volcanic island in Russia’s Kuril Islands chain known for its caldera and geothermal activity.
  • B. URU
    URU is the FIFA country code used to represent the Uruguay national football team in international competitions and rankings.
  • C. URMO
    URMO is the ICAO airport code for Beslan Airport, which serves the city of Vladikavkaz in North Ossetia–Alania, Russia.
  • D. Rumuokurusi
    Rumuokurusi is a prominent urban community in Obio-Akpor, Rivers State, Nigeria, known for its commercial activity and strategic location within the Port Harcourt metropolitan area.
  • E. Komuro
    Komuro is the married surname of Japan’s former Princess Mako, adopted after her marriage to commoner Kei Komuro.
  • 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_69ca835edb4481909b4aafb616dc5eb7 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5f2dc87c8190be0597a260d95a0b completed March 31, 2026, 11:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf51c0125c819098deb7a54688b125 completed April 3, 2026, 5:36 a.m.
NEDg Description generation batch_69cf5378c3f48190a4180c20aecb2260 completed April 3, 2026, 5:43 a.m.
NED2 Entity disambiguation (via description) batch_69cf5471e9c08190963b7f1d6c2ceffe completed April 3, 2026, 5:47 a.m.
Created at: March 30, 2026, 6:41 p.m.