Triple

T15638242
Position Surface form Disambiguated ID Type / Status
Subject Jhulelal E375999 entity
Predicate honorificTitle P2097 FINISHED
Object Darya Shah
Darya Shah is a reverential title associated with the Sindhi deity Jhulelal, emphasizing his status as a spiritual sovereign or saintly figure.
E1173227 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: Darya Shah | Statement: [Jhulelal, honorificTitle, Darya Shah]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Darya Shah
Context triple: [Jhulelal, honorificTitle, Darya Shah]
  • A. Dora Esmailian
    Dora Esmailian is a film editor known for her work on the movie "Miracle Mile."
  • B. Shahrzad Davani
    Shahrzad Davani is a film producer best known for her work on the biographical drama "Brain on Fire."
  • C. Sofia Akrami
    Sofia Akrami is a woman known primarily as the mother of Amir.
  • D. Sia Alipour
    Sia Alipour is an actor known for his role in the Iranian television series "Tehran."
  • E. Sediqa Massoud
    Sediqa Massoud is the widow of famed Afghan resistance leader Ahmad Shah Massoud and a prominent advocate for women's rights and education in Afghanistan.
  • 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: Darya Shah
Triple: [Jhulelal, honorificTitle, Darya Shah]
Generated description
Darya Shah is a reverential title associated with the Sindhi deity Jhulelal, emphasizing his status as a spiritual sovereign or saintly figure.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Darya Shah
Target entity description: Darya Shah is a reverential title associated with the Sindhi deity Jhulelal, emphasizing his status as a spiritual sovereign or saintly figure.
  • A. Dora Esmailian
    Dora Esmailian is a film editor known for her work on the movie "Miracle Mile."
  • B. Shahrzad Davani
    Shahrzad Davani is a film producer best known for her work on the biographical drama "Brain on Fire."
  • C. Sofia Akrami
    Sofia Akrami is a woman known primarily as the mother of Amir.
  • D. Sia Alipour
    Sia Alipour is an actor known for his role in the Iranian television series "Tehran."
  • E. Sediqa Massoud
    Sediqa Massoud is the widow of famed Afghan resistance leader Ahmad Shah Massoud and a prominent advocate for women's rights and education in Afghanistan.
  • 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_69d85cd035a48190b73d5579ab73969a completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04eba51f08190ac5d9de7fc89405a completed April 16, 2026, 2:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff82e921e48190b5b5f4006ad65844 completed May 9, 2026, 6:54 p.m.
NEDg Description generation batch_69ff8378450081909614f68772a23851 completed May 9, 2026, 6:56 p.m.
NED2 Entity disambiguation (via description) batch_69ff84125e808190a4d465d9effad639 completed May 9, 2026, 6:59 p.m.
Created at: April 10, 2026, 4:14 a.m.