Triple

T1023037
Position Surface form Disambiguated ID Type / Status
Subject Tarim Basin E22080 entity
Predicate ancientLanguages P23482 FINISHED
Object Saka
Saka is an ancient Eastern Iranian language once spoken by the Saka people in the Tarim Basin region of Central Asia.
 E123639 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: Saka | Statement: [Tarim Basin, ancientLanguages, Saka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Saka
Context triple: [Tarim Basin, ancientLanguages, Saka]
  • A. Hira
    Hira is the ISO 15924 script code representing the Japanese hiragana writing system.
  • B. Raka
    Raka is a renowned Afrikaans narrative poem by N. P. van Wyk Louw that explores themes of civilization, barbarism, and moral conflict through an allegorical tale.
  • C. Kish
    Kish is a Benjaminite figure in the Hebrew Bible best known as the father of Israel’s first king, Saul.
  • D. Sakae
    Sakae is a major downtown commercial and entertainment district in Nagoya, Japan, known for its shopping, nightlife, and landmark attractions.
  • E. Seoni
    Seoni is a town and district headquarters in the central Indian state of Madhya Pradesh, known for its proximity to Pench National Park and its association with Rudyard Kipling’s "The Jungle Book."
  • 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: Saka
Triple: [Tarim Basin, ancientLanguages, Saka]
Generated description
Saka is an ancient Eastern Iranian language once spoken by the Saka people in the Tarim Basin region of Central Asia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Saka
Target entity description: Saka is an ancient Eastern Iranian language once spoken by the Saka people in the Tarim Basin region of Central Asia.
  • A. Hira
    Hira is the ISO 15924 script code representing the Japanese hiragana writing system.
  • B. Raka
    Raka is a renowned Afrikaans narrative poem by N. P. van Wyk Louw that explores themes of civilization, barbarism, and moral conflict through an allegorical tale.
  • C. Kish
    Kish is a Benjaminite figure in the Hebrew Bible best known as the father of Israel’s first king, Saul.
  • D. Sakae
    Sakae is a major downtown commercial and entertainment district in Nagoya, Japan, known for its shopping, nightlife, and landmark attractions.
  • E. Seoni
    Seoni is a town and district headquarters in the central Indian state of Madhya Pradesh, known for its proximity to Pench National Park and its association with Rudyard Kipling’s "The Jungle Book."
  • 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_69a493d6e380819097b384986ffc315c completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4bb71e7f88190bf33bbe5ef2c68ff completed March 1, 2026, 10:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac42947f2c8190b83c6b958987cb7b completed March 7, 2026, 3:21 p.m.
NEDg Description generation batch_69ac43d060608190b8c5ce73b95bee46 completed March 7, 2026, 3:27 p.m.
NED2 Entity disambiguation (via description) batch_69ac443cdea081909b937aba21d878c7 completed March 7, 2026, 3:29 p.m.
Created at: March 1, 2026, 7:41 p.m.