Triple

T10912006
Position Surface form Disambiguated ID Type / Status
Subject Datooga E257722 entity
Predicate hasNeighborLanguage P16383 FINISHED
Object Rangi
Rangi is a Bantu language spoken primarily in north-central Tanzania.
E892749 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: Rangi | Statement: [Datooga, hasNeighborLanguage, Rangi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rangi
Context triple: [Datooga, hasNeighborLanguage, Rangi]
  • A. Turangi
    Turangi is a small town in New Zealand’s central North Island, known as a gateway to Tongariro National Park and popular for trout fishing and outdoor recreation.
  • B. Rongo
    Rongo is a major Polynesian deity commonly associated with cultivated food, especially sweet potatoes, as well as peace and agriculture.
  • C. Rangea
    Rangea is an extinct frond-shaped organism from the Ediacaran Period, known as one of the earliest complex multicellular life forms preserved in Precambrian fossil beds.
  • D. Poutoru
    Poutoru is the principal village and administrative center of the island of Taha'a in French Polynesia.
  • E. Bungarange
    Bungarange is an alternative name for the Bangerang, an Aboriginal Australian people traditionally associated with parts of northern Victoria and southern New South Wales.
  • 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: Rangi
Triple: [Datooga, hasNeighborLanguage, Rangi]
Generated description
Rangi is a Bantu language spoken primarily in north-central Tanzania.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Rangi
Target entity description: Rangi is a Bantu language spoken primarily in north-central Tanzania.
  • A. Turangi
    Turangi is a small town in New Zealand’s central North Island, known as a gateway to Tongariro National Park and popular for trout fishing and outdoor recreation.
  • B. Rongo
    Rongo is a major Polynesian deity commonly associated with cultivated food, especially sweet potatoes, as well as peace and agriculture.
  • C. Rangea
    Rangea is an extinct frond-shaped organism from the Ediacaran Period, known as one of the earliest complex multicellular life forms preserved in Precambrian fossil beds.
  • D. Poutoru
    Poutoru is the principal village and administrative center of the island of Taha'a in French Polynesia.
  • E. Bungarange
    Bungarange is an alternative name for the Bangerang, an Aboriginal Australian people traditionally associated with parts of northern Victoria and southern New South Wales.
  • 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_69d6aa864ed88190818280ab6791d065 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d770723df08190bedfdc94d998f969 completed April 9, 2026, 9:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69e155550e388190bd441ac3a9dde435 completed April 16, 2026, 9:32 p.m.
NEDg Description generation batch_69e1801eaa048190a5e8822b3da1077c completed April 17, 2026, 12:34 a.m.
NED2 Entity disambiguation (via description) batch_69e1831f8a6c819084bde8f71371cf8e completed April 17, 2026, 12:47 a.m.
Created at: April 8, 2026, 9:22 p.m.