Triple

T13713150
Position Surface form Disambiguated ID Type / Status
Subject Harmonize E328824 entity
Predicate alsoKnownAs P39 FINISHED
Object Jeshi
Jeshi is a Tanzanian singer and songwriter best known as a member of the popular Bongo Flava music group Harmonize.
 E1058059 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: Jeshi | Statement: [Harmonize, alsoKnownAs, Jeshi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Jeshi
Context triple: [Harmonize, alsoKnownAs, Jeshi]
  • A. Jish
    Jish is a village in northern Israel, historically significant for its mixed Maronite Christian and Muslim population and its location near the Lebanese border.
  • B. Jetha
    Jetha is the birth name of Guru Ram Das, the fourth Sikh Guru and a central figure in Sikh religious history.
  • C. Jashub
    Jashub is a biblical figure mentioned in the Hebrew Bible as one of the descendants of Jacob through the tribe of Issachar.
  • D. Jeush
    Jeush is a minor biblical figure mentioned in the Hebrew Bible as one of the sons in Esau’s family line.
  • E. Junshi
    Junshi was the courtesy name of Sima Guang, a prominent Song dynasty historian and statesman best known for compiling the comprehensive chronicle "Zizhi Tongjian."
  • 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: Jeshi
Triple: [Harmonize, alsoKnownAs, Jeshi]
Generated description
Jeshi is a Tanzanian singer and songwriter best known as a member of the popular Bongo Flava music group Harmonize.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Jeshi
Target entity description: Jeshi is a Tanzanian singer and songwriter best known as a member of the popular Bongo Flava music group Harmonize.
  • A. Jish
    Jish is a village in northern Israel, historically significant for its mixed Maronite Christian and Muslim population and its location near the Lebanese border.
  • B. Jetha
    Jetha is the birth name of Guru Ram Das, the fourth Sikh Guru and a central figure in Sikh religious history.
  • C. Jashub
    Jashub is a biblical figure mentioned in the Hebrew Bible as one of the descendants of Jacob through the tribe of Issachar.
  • D. Jeush
    Jeush is a minor biblical figure mentioned in the Hebrew Bible as one of the sons in Esau’s family line.
  • E. Junshi
    Junshi was the courtesy name of Sima Guang, a prominent Song dynasty historian and statesman best known for compiling the comprehensive chronicle "Zizhi Tongjian."
  • 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_69d80770b9bc81909f70c8c317d53cff completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dd4395e8c0819098719c8cd344aa33 completed April 13, 2026, 7:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69f79d56a90081908158dcf4ee061fb6 completed May 3, 2026, 7:09 p.m.
NEDg Description generation batch_69f7a15f3c908190be380355972def6e completed May 3, 2026, 7:26 p.m.
NED2 Entity disambiguation (via description) batch_69f7a2234390819093814fd435f9c42c completed May 3, 2026, 7:29 p.m.
Created at: April 9, 2026, 9:54 p.m.