Triple

T11582619
Position Surface form Disambiguated ID Type / Status
Subject Tumbuka E274665 entity
Predicate iso639-2Code P208 FINISHED
Object tum
"tum" is the ISO 639-2 language code for Tumbuka, a Bantu language spoken primarily in Malawi and parts of Zambia and Tanzania.
 E934807 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: tum | Statement: [Tumbuka, iso639-2Code, tum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: tum
Context triple: [Tumbuka, iso639-2Code, tum]
  • A. tumdak
    The tumdak is a traditional drum used by the Santhal people, central to their folk music and ceremonial performances.
  • B. tundama
    Tundama was a prominent Muisca ruler (cacique) known for leading resistance against the Spanish conquest in what is now central Colombia.
  • C. TUM SOT
    TUM SOT is the TUM School of Social Sciences and Technology at the Technical University of Munich, focusing on the intersection of social sciences, technology, and policy.
  • D. tet
    tet is the ISO 639-1 language code for Tetum, an Austronesian language spoken primarily in East Timor.
  • E. Tumladen
    Tumladen is a hidden, fertile valley in J.R.R. Tolkien’s legendarium, famed as the secluded site of the Elven city of Gondolin in Beleriand.
  • 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: tum
Triple: [Tumbuka, iso639-2Code, tum]
Generated description
"tum" is the ISO 639-2 language code for Tumbuka, a Bantu language spoken primarily in Malawi and parts of Zambia and Tanzania.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: tum
Target entity description: "tum" is the ISO 639-2 language code for Tumbuka, a Bantu language spoken primarily in Malawi and parts of Zambia and Tanzania.
  • A. tumdak
    The tumdak is a traditional drum used by the Santhal people, central to their folk music and ceremonial performances.
  • B. tundama
    Tundama was a prominent Muisca ruler (cacique) known for leading resistance against the Spanish conquest in what is now central Colombia.
  • C. TUM SOT
    TUM SOT is the TUM School of Social Sciences and Technology at the Technical University of Munich, focusing on the intersection of social sciences, technology, and policy.
  • D. tet
    tet is the ISO 639-1 language code for Tetum, an Austronesian language spoken primarily in East Timor.
  • E. Tumladen
    Tumladen is a hidden, fertile valley in J.R.R. Tolkien’s legendarium, famed as the secluded site of the Elven city of Gondolin in Beleriand.
  • 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_69d6aae6b14c81908dc5a74bad7591f9 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8904db5748190ae5f10ae86ccdf46 completed April 10, 2026, 5:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69e7142d442c8190a48372e0e17db517 completed April 21, 2026, 6:07 a.m.
NEDg Description generation batch_69e720fb192881909c129f93c8b88f42 completed April 21, 2026, 7:02 a.m.
NED2 Entity disambiguation (via description) batch_69e7233efb6c81909dbf1aef080f5598 completed April 21, 2026, 7:11 a.m.
Created at: April 8, 2026, 9:38 p.m.