Triple

T19078454
Position Surface form Disambiguated ID Type / Status
Subject Table of Nations E466961 entity
Predicate mentionsRegion P35463 FINISHED
Object Shinar
Shinar is an ancient biblical region, often associated with Mesopotamia and the setting of narratives such as the Tower of Babel.
 E1358554 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: Shinar | Statement: [Table of Nations, mentionsRegion, Shinar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Shinar
Context triple: [Table of Nations, mentionsRegion, Shinar]
  • A. Yesan
    Yesan is an alternate name for the Tutelo language, a nearly extinct Siouan language historically spoken by the Tutelo people of eastern North America.
  • B. Yishai
    Yishai is the Hebrew form of the biblical name Jesse, known as the father of King David in the Hebrew Bible.
  • C. Yarden
    Yarden is the Hebrew name for the Jordan River, a historically and religiously significant river in the Middle East.
  • D. Rehavia
    Rehavia is a historic, centrally located Jerusalem neighborhood known for its leafy streets, Bauhaus-style architecture, and mix of intellectual, political, and cultural residents.
  • E. Binyamina
    Binyamina is a town in northern Israel known for its vineyards, wineries, and role as a regional transportation hub.
  • 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: Shinar
Triple: [Table of Nations, mentionsRegion, Shinar]
Generated description
Shinar is an ancient biblical region, often associated with Mesopotamia and the setting of narratives such as the Tower of Babel.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Shinar
Target entity description: Shinar is an ancient biblical region, often associated with Mesopotamia and the setting of narratives such as the Tower of Babel.
  • A. Yesan
    Yesan is an alternate name for the Tutelo language, a nearly extinct Siouan language historically spoken by the Tutelo people of eastern North America.
  • B. Yishai
    Yishai is the Hebrew form of the biblical name Jesse, known as the father of King David in the Hebrew Bible.
  • C. Yarden
    Yarden is the Hebrew name for the Jordan River, a historically and religiously significant river in the Middle East.
  • D. Rehavia
    Rehavia is a historic, centrally located Jerusalem neighborhood known for its leafy streets, Bauhaus-style architecture, and mix of intellectual, political, and cultural residents.
  • E. Binyamina
    Binyamina is a town in northern Israel known for its vineyards, wineries, and role as a regional transportation hub.
  • 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_69d8dd04f4488190b1121cc53ef2bfd6 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e2e61b60819092d42614f04a087c completed April 20, 2026, 8:25 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05dd8ec26c8190937a48220d165fa5 completed May 14, 2026, 2:34 p.m.
NEDg Description generation batch_6a05e1e3adcc819085c5044918fe2178 completed May 14, 2026, 2:53 p.m.
NED2 Entity disambiguation (via description) batch_6a05e240abdc81909b9486e6027d5756 completed May 14, 2026, 2:54 p.m.
Created at: April 10, 2026, 12:04 p.m.