Triple

T10612613
Position Surface form Disambiguated ID Type / Status
Subject Japji Sahib E276042 entity
Predicate timeOfRecitation P1936 FINISHED
Object Amrit Vela
Amrit Vela is the pre-dawn period in Sikhism considered especially sacred for meditation, prayer, and spiritual practice.
E874855 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: Amrit Vela | Statement: [Japji Sahib, timeOfRecitation, Amrit Vela]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Amrit Vela
Context triple: [Japji Sahib, timeOfRecitation, Amrit Vela]
  • A. Savyasachi
    Savyasachi is a celebrated epithet of the Mahabharata hero Arjuna, highlighting his legendary ambidextrous skill in archery and combat.
  • B. Pingali Surana
    Pingali Surana was a prominent 16th-century Telugu poet and writer of the Vijayanagara era, renowned for his classical works such as "Kalapurnodayam."
  • C. Vivek
    Vivek is a common Indian male given name, notably borne by entrepreneur and NBA team owner Vivek Ranadivé.
  • D. Vasanth
    Vasanth is an Indian film director and screenwriter known for his work in Tamil cinema, often noted for his sensitive storytelling and character-driven narratives.
  • E. Mita Vashisht
    Mita Vashisht is an Indian film, television, and theatre actress known for her powerful character roles and performances in both mainstream and parallel cinema.
  • 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: Amrit Vela
Triple: [Japji Sahib, timeOfRecitation, Amrit Vela]
Generated description
Amrit Vela is the pre-dawn period in Sikhism considered especially sacred for meditation, prayer, and spiritual practice.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Amrit Vela
Target entity description: Amrit Vela is the pre-dawn period in Sikhism considered especially sacred for meditation, prayer, and spiritual practice.
  • A. Savyasachi
    Savyasachi is a celebrated epithet of the Mahabharata hero Arjuna, highlighting his legendary ambidextrous skill in archery and combat.
  • B. Pingali Surana
    Pingali Surana was a prominent 16th-century Telugu poet and writer of the Vijayanagara era, renowned for his classical works such as "Kalapurnodayam."
  • C. Vivek
    Vivek is a common Indian male given name, notably borne by entrepreneur and NBA team owner Vivek Ranadivé.
  • D. Vasanth
    Vasanth is an Indian film director and screenwriter known for his work in Tamil cinema, often noted for his sensitive storytelling and character-driven narratives.
  • E. Mita Vashisht
    Mita Vashisht is an Indian film, television, and theatre actress known for her powerful character roles and performances in both mainstream and parallel cinema.
  • 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_69d6aaf948d88190806cc3a8c47a3fb2 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d6df5baf94819097b14a73af058f35 completed April 8, 2026, 11:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69d95ec61b388190adee9b3577567709 completed April 10, 2026, 8:34 p.m.
NEDg Description generation batch_69d95f824b3081908561f0d3748e3713 completed April 10, 2026, 8:37 p.m.
NED2 Entity disambiguation (via description) batch_69d9600a29808190af583d2fd696ec6a completed April 10, 2026, 8:39 p.m.
Created at: April 8, 2026, 7:33 p.m.