Triple

T923549
Position Surface form Disambiguated ID Type / Status
Subject Shiva E19933 entity
Predicate mount P18930 FINISHED
Object Nandi
Nandi is the sacred bull and devoted gatekeeper of the Hindu god Shiva, revered as a symbol of strength, righteousness, and dharma.
 E111278 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: Nandi | Statement: [Shiva, mount, Nandi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Nandi
Context triple: [Shiva, mount, Nandi]
  • A. The Mara
    The Mara is a quick-service restaurant at Disney’s Animal Kingdom Lodge offering African-inspired and American dishes in a casual setting.
  • B. Nyanda
    Nyanda is the former name of Masvingo, a historic city in southeastern Zimbabwe known for its proximity to the Great Zimbabwe ruins.
  • C. Ngozi
    Ngozi is a Nigerian given name of Igbo origin commonly used for females and meaning "blessing."
  • D. Derawali
    Derawali is a regional dialect of the Saraiki language spoken primarily in and around the Dera Ghazi Khan and Dera Ismail Khan areas of Pakistan.
  • E. Gigiri
    Gigiri is an affluent diplomatic and residential district in Nairobi, Kenya, known for hosting major international institutions and embassies.
  • 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: Nandi
Triple: [Shiva, mount, Nandi]
Generated description
Nandi is the sacred bull and devoted gatekeeper of the Hindu god Shiva, revered as a symbol of strength, righteousness, and dharma.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Nandi
Target entity description: Nandi is the sacred bull and devoted gatekeeper of the Hindu god Shiva, revered as a symbol of strength, righteousness, and dharma.
  • A. The Mara
    The Mara is a quick-service restaurant at Disney’s Animal Kingdom Lodge offering African-inspired and American dishes in a casual setting.
  • B. Nyanda
    Nyanda is the former name of Masvingo, a historic city in southeastern Zimbabwe known for its proximity to the Great Zimbabwe ruins.
  • C. Ngozi
    Ngozi is a Nigerian given name of Igbo origin commonly used for females and meaning "blessing."
  • D. Derawali
    Derawali is a regional dialect of the Saraiki language spoken primarily in and around the Dera Ghazi Khan and Dera Ismail Khan areas of Pakistan.
  • E. Gigiri
    Gigiri is an affluent diplomatic and residential district in Nairobi, Kenya, known for hosting major international institutions and embassies.
  • 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_69a493a099788190a696d9d8408cbaf4 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4b3296f50819087f809fbe90b139e completed March 1, 2026, 9:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69a826d8f9408190aa286bb809507797 completed March 4, 2026, 12:34 p.m.
NEDg Description generation batch_69a84d53e46c8190b19b56ecc928c9a0 completed March 4, 2026, 3:18 p.m.
NED2 Entity disambiguation (via description) batch_69a84db197448190897d0def5f01a2c2 completed March 4, 2026, 3:20 p.m.
Created at: March 1, 2026, 7:40 p.m.