Triple

T1494149
Position Surface form Disambiguated ID Type / Status
Subject Siwi E29648 entity
Predicate hasAlternativeName P39 FINISHED
Object Tasiwit
Tasiwit is an alternative name for Siwi, a Berber language spoken in Egypt’s Siwa Oasis.
E170857 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: Tasiwit | Statement: [Siwi, hasAlternativeName, Tasiwit]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tasiwit
Context triple: [Siwi, hasAlternativeName, Tasiwit]
  • A. Mae Sot
    Mae Sot is a Thai border town in Tak Province known as a major hub for cross-border trade and migration with Myanmar and for its numerous refugee and humanitarian aid organizations.
  • B. Bantia
    Bantia was an ancient Oscan-speaking city in southern Italy, notable for yielding important inscriptions that illuminate the Oscan language and Italic legal traditions.
  • C. Sulak
    Sulak is a Thai social activist and Buddhist scholar known for his advocacy of human rights, democracy, and engaged Buddhism.
  • D. Sassi Punnun
    Sassi Punnun is a legendary romantic tragic tale from Punjabi (and broader South Asian) folklore, often celebrated as one of the classic love stories of the region.
  • E. Lao Phra Lak Phra Lam
    Lao Phra Lak Phra Lam is the Lao national epic, a localized adaptation of the Indian Ramayana that reflects Lao culture, religion, and literary tradition.
  • 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: Tasiwit
Triple: [Siwi, hasAlternativeName, Tasiwit]
Generated description
Tasiwit is an alternative name for Siwi, a Berber language spoken in Egypt’s Siwa Oasis.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tasiwit
Target entity description: Tasiwit is an alternative name for Siwi, a Berber language spoken in Egypt’s Siwa Oasis.
  • A. Tambolaka
    Tambolaka is a town on the Indonesian island of Sumba that serves as an important local hub with an airport and access point for exploring the island.
  • B. Mae Sot
    Mae Sot is a Thai border town in Tak Province known as a major hub for cross-border trade and migration with Myanmar and for its numerous refugee and humanitarian aid organizations.
  • C. Bantia
    Bantia was an ancient Oscan-speaking city in southern Italy, notable for yielding important inscriptions that illuminate the Oscan language and Italic legal traditions.
  • D. Sulak
    Sulak is a Thai social activist and Buddhist scholar known for his advocacy of human rights, democracy, and engaged Buddhism.
  • E. Sassi Punnun
    Sassi Punnun is a legendary romantic tragic tale from Punjabi (and broader South Asian) folklore, often celebrated as one of the classic love stories of the region.
  • 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_69a498dba1d8819093b46a3a8d2485f1 completed March 1, 2026, 7:51 p.m.
NER Named-entity recognition batch_69a4c6c665488190ae665f7a1b0563f5 completed March 1, 2026, 11:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad1cabe25c8190ba1d285a210a00f0 completed March 8, 2026, 6:52 a.m.
NEDg Description generation batch_69ad1fb7e4448190a7bca159cd5a4be7 completed March 8, 2026, 7:05 a.m.
NED2 Entity disambiguation (via description) batch_69ad2014a0c481908f2f66fc742fa90f completed March 8, 2026, 7:07 a.m.
Created at: March 1, 2026, 8:12 p.m.