Triple

T7103241
Position Surface form Disambiguated ID Type / Status
Subject Manupeu Tanah Daru National Park E165510 entity
Predicate hasEndemicSpecies P954 FINISHED
Object Sumba myzomela
The Sumba myzomela is a small, nectar-feeding honeyeater bird species found only on the Indonesian island of Sumba.
 E642384 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: Sumba myzomela | Statement: [Manupeu Tanah Daru National Park, hasEndemicSpecies, Sumba myzomela]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sumba myzomela
Context triple: [Manupeu Tanah Daru National Park, hasEndemicSpecies, Sumba myzomela]
  • A. Sumba boobook
    The Sumba boobook is a small, nocturnal owl species found only on the Indonesian island of Sumba.
  • B. Umbundu
    Umbundu is a major Bantu language spoken primarily in central and southern Angola, especially by the Ovimbundu people.
  • C. Kikamba-Doondo
    Kikamba-Doondo is a regional dialect of the Bantu language Kikongo, spoken by communities in parts of Central Africa.
  • D. Oshikwanyama
    Oshikwanyama is a Bantu language variety spoken primarily in northern Namibia and southern Angola, recognized as one of the major dialects of Oshiwambo.
  • E. Mimiambi
    Mimiambi are a collection of Hellenistic Greek mimes in verse, most famously composed by Herodas, that depict everyday life and characters in a vivid, colloquial style.
  • 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: Sumba myzomela
Triple: [Manupeu Tanah Daru National Park, hasEndemicSpecies, Sumba myzomela]
Generated description
The Sumba myzomela is a small, nectar-feeding honeyeater bird species found only on the Indonesian island of Sumba.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sumba myzomela
Target entity description: The Sumba myzomela is a small, nectar-feeding honeyeater bird species found only on the Indonesian island of Sumba.
  • A. Sumba boobook
    The Sumba boobook is a small, nocturnal owl species found only on the Indonesian island of Sumba.
  • B. Umbundu
    Umbundu is a major Bantu language spoken primarily in central and southern Angola, especially by the Ovimbundu people.
  • C. Kikamba-Doondo
    Kikamba-Doondo is a regional dialect of the Bantu language Kikongo, spoken by communities in parts of Central Africa.
  • D. Oshikwanyama
    Oshikwanyama is a Bantu language variety spoken primarily in northern Namibia and southern Angola, recognized as one of the major dialects of Oshiwambo.
  • E. Mimiambi
    Mimiambi are a collection of Hellenistic Greek mimes in verse, most famously composed by Herodas, that depict everyday life and characters in a vivid, colloquial style.
  • 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_69c6887fcddc8190a5d58908f6dee590 completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e58a0a2c819088e0c8874fb4491f completed March 27, 2026, 8:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69c79cad60788190bb2b17d1c3f8e1cc completed March 28, 2026, 9:17 a.m.
NEDg Description generation batch_69c79d72dd70819084a4bf7e72865ed9 completed March 28, 2026, 9:20 a.m.
NED2 Entity disambiguation (via description) batch_69c79e12a40c8190b21128e17c3e212e completed March 28, 2026, 9:23 a.m.
Created at: March 27, 2026, 2:42 p.m.