Triple

T11012481
Position Surface form Disambiguated ID Type / Status
Subject Kam language E260275 entity
Predicate autonym P1435 FINISHED
Object Gaeml
Gaeml is the self-designated name used by speakers of the Kam language, a Tai–Kadai language spoken primarily in southern China.
 E899582 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: Gaeml | Statement: [Kam language, autonym, Gaeml]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gaeml
Context triple: [Kam language, autonym, Gaeml]
  • A. Gamzatti
    Gamzatti is the proud and aristocratic daughter of the Rajah and rival to the temple dancer Nikiya in the classical ballet *La Bayadère*.
  • B. Germi
    Germi is a city in northwestern Iran known for its location in Ardabil Province near the border with the Republic of Azerbaijan.
  • C. Gamilah
    Gamilah is one of the daughters of Malcolm X and Betty Shabazz, known for her connection to their civil rights legacy.
  • D. Gra
    Gra, an acronym for the Vilna Gaon (Rabbi Elijah ben Solomon Zalman), was an 18th-century Lithuanian Jewish sage renowned for his profound Talmudic, halachic, and Kabbalistic scholarship.
  • E. Gamelia
    Gamelia is an epithet associated with the Greek goddess Hera, emphasizing her role as protector of marriage and weddings.
  • 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: Gaeml
Triple: [Kam language, autonym, Gaeml]
Generated description
Gaeml is the self-designated name used by speakers of the Kam language, a Tai–Kadai language spoken primarily in southern China.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gaeml
Target entity description: Gaeml is the self-designated name used by speakers of the Kam language, a Tai–Kadai language spoken primarily in southern China.
  • A. Gamzatti
    Gamzatti is the proud and aristocratic daughter of the Rajah and rival to the temple dancer Nikiya in the classical ballet *La Bayadère*.
  • B. Germi
    Germi is a city in northwestern Iran known for its location in Ardabil Province near the border with the Republic of Azerbaijan.
  • C. Gamilah
    Gamilah is one of the daughters of Malcolm X and Betty Shabazz, known for her connection to their civil rights legacy.
  • D. Gra
    Gra, an acronym for the Vilna Gaon (Rabbi Elijah ben Solomon Zalman), was an 18th-century Lithuanian Jewish sage renowned for his profound Talmudic, halachic, and Kabbalistic scholarship.
  • E. Gamelia
    Gamelia is an epithet associated with the Greek goddess Hera, emphasizing her role as protector of marriage and weddings.
  • 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_69d6aa9687448190b28d353b1b6a610e completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7978a57a881909b4ceae0ebe21b78 completed April 9, 2026, 12:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69e374ac78348190a8c0a5a7a736b24b completed April 18, 2026, 12:10 p.m.
NEDg Description generation batch_69e378df767c819099d0bfdf35eaf5f3 completed April 18, 2026, 12:28 p.m.
NED2 Entity disambiguation (via description) batch_69e37bf526108190b5fc22569fe6be54 completed April 18, 2026, 12:41 p.m.
Created at: April 8, 2026, 9:25 p.m.