Triple

T18763928
Position Surface form Disambiguated ID Type / Status
Subject HAL HJT-36 Sitara E458844 entity
Predicate aircraftFamily P1524 FINISHED
Object HJT-36
HJT-36 is an Indian intermediate jet trainer aircraft developed by Hindustan Aeronautics Limited (HAL) to train military pilots in advanced flying and combat skills.
E1341962 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: HJT-36 | Statement: [HAL HJT-36 Sitara, aircraftFamily, HJT-36]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: HJT-36
Context triple: [HAL HJT-36 Sitara, aircraftFamily, HJT-36]
  • A. GJ-16
    GJ-16 is the vehicle registration code assigned to the Bharuch district in the Indian state of Gujarat.
  • B. GJ-3
    GJ-3 is the regional vehicle registration code assigned to the city of Rajkot in the Indian state of Gujarat.
  • C. JFT-300M
    JFT-300M is a massive proprietary image classification dataset containing around 300 million labeled images used to pretrain large-scale vision models.
  • D. SH-364
    SH-364 is the Oklahoma state highway designation for the Creek Turnpike, a toll road serving the Tulsa metropolitan area.
  • E. GJ-24
    GJ-24 is the vehicle registration code assigned to motor vehicles registered in Patan district of Gujarat, India.
  • 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: HJT-36
Triple: [HAL HJT-36 Sitara, aircraftFamily, HJT-36]
Generated description
HJT-36 is an Indian intermediate jet trainer aircraft developed by Hindustan Aeronautics Limited (HAL) to train military pilots in advanced flying and combat skills.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: HJT-36
Target entity description: HJT-36 is an Indian intermediate jet trainer aircraft developed by Hindustan Aeronautics Limited (HAL) to train military pilots in advanced flying and combat skills.
  • A. GJ-16
    GJ-16 is the vehicle registration code assigned to the Bharuch district in the Indian state of Gujarat.
  • B. GJ-3
    GJ-3 is the regional vehicle registration code assigned to the city of Rajkot in the Indian state of Gujarat.
  • C. JFT-300M
    JFT-300M is a massive proprietary image classification dataset containing around 300 million labeled images used to pretrain large-scale vision models.
  • D. SH-364
    SH-364 is the Oklahoma state highway designation for the Creek Turnpike, a toll road serving the Tulsa metropolitan area.
  • E. GJ-24
    GJ-24 is the vehicle registration code assigned to motor vehicles registered in Patan district of Gujarat, India.
  • 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_69d8d395dba0819087568404508590cb completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e58d82297c81909f720e2637cec737 completed April 20, 2026, 2:20 a.m.
NED1 Entity disambiguation (via context triple) batch_6a053d407b0c819090e6d66430db4a39 completed May 14, 2026, 3:10 a.m.
NEDg Description generation batch_6a053df532c48190b153dd9f790f1cc8 completed May 14, 2026, 3:13 a.m.
NED2 Entity disambiguation (via description) batch_6a0541e2d4008190a8beb79812ccf485 completed May 14, 2026, 3:30 a.m.
Created at: April 10, 2026, 11:52 a.m.