Triple

T6186929
Position Surface form Disambiguated ID Type / Status
Subject Shíshálh Nation E138083 entity
Predicate hasLanguage P15 FINISHED
Object sháshíshálhem
sháshíshálhem is the traditional Coast Salish language spoken by the Shíshálh (Sechelt) people of British Columbia, Canada.
 E576397 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: sháshíshálhem | Statement: [Shíshálh Nation, hasLanguage, sháshíshálhem]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: sháshíshálhem
Context triple: [Shíshálh Nation, hasLanguage, sháshíshálhem]
  • A. ŠA
    ŠA is the regional vehicle registration code used on license plates for the city of Šabac in Serbia.
  • B. ashik
    An ashik is a traditional Turkic bard and folk musician who performs narrative poetry and epic tales, often accompanying themselves on a long-necked lute.
  • C. SH
    SH is the common abbreviation for Södertörn University, a higher education institution located in the Stockholm region of Sweden.
  • D. Huvishka
    Huvishka was a prominent Kushan emperor of the 2nd century CE, known for his extensive coinage and role in consolidating the empire’s power and cultural diversity across Central and South Asia.
  • E. Sh1
    Sh1 is a Georgian mountain road route that traverses the Goderdzi Pass, connecting regions across the Lesser Caucasus.
  • 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: sháshíshálhem
Triple: [Shíshálh Nation, hasLanguage, sháshíshálhem]
Generated description
sháshíshálhem is the traditional Coast Salish language spoken by the Shíshálh (Sechelt) people of British Columbia, Canada.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: sháshíshálhem
Target entity description: sháshíshálhem is the traditional Coast Salish language spoken by the Shíshálh (Sechelt) people of British Columbia, Canada.
  • A. ŠA
    ŠA is the regional vehicle registration code used on license plates for the city of Šabac in Serbia.
  • B. ashik
    An ashik is a traditional Turkic bard and folk musician who performs narrative poetry and epic tales, often accompanying themselves on a long-necked lute.
  • C. SH
    SH is the common abbreviation for Södertörn University, a higher education institution located in the Stockholm region of Sweden.
  • D. Huvishka
    Huvishka was a prominent Kushan emperor of the 2nd century CE, known for his extensive coinage and role in consolidating the empire’s power and cultural diversity across Central and South Asia.
  • E. Sh1
    Sh1 is a Georgian mountain road route that traverses the Goderdzi Pass, connecting regions across the Lesser Caucasus.
  • 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_69c008a8fd408190b7ec6e42934974a6 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0621671988190938dd16242a2e4d5 completed March 22, 2026, 9:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69c16effda2481909dad5732077cf1d3 completed March 23, 2026, 4:49 p.m.
NEDg Description generation batch_69c1bf1abd9881908c726c090f56b2f4 completed March 23, 2026, 10:30 p.m.
NED2 Entity disambiguation (via description) batch_69c1bfba7a9881909545138859ab8c48 completed March 23, 2026, 10:33 p.m.
Created at: March 22, 2026, 4:19 p.m.