Triple

T3857958
Position Surface form Disambiguated ID Type / Status
Subject Bilen E90064 entity
Predicate region P40 FINISHED
Object Keren
Keren is a major town in Eritrea known as an important commercial and agricultural center in the Anseba region.
 E392868 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: Keren | Statement: [Bilen, region, Keren]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Keren
Context triple: [Bilen, region, Keren]
  • A. Sharona Katan
    Sharona Katan is an Israeli-born visual artist and the wife of Radiohead guitarist and composer Jonny Greenwood.
  • B. Alona Tal
    Alona Tal is an Israeli-American actress and singer known for her roles in television series such as "Veronica Mars," "Supernatural," and "Hand of God."
  • C. Rachel Dayan
    Rachel Dayan was the wife of prominent Israeli military leader and politician Moshe Dayan.
  • D. Yoni Brenner
    Yoni Brenner is a screenwriter and humorist known for his work on animated films, including contributing to the screenplay of "Rio 2."
  • E. Tamara Geva
    Tamara Geva was a Russian-American dancer and actress known for her early collaborations with choreographer George Balanchine and her influential work on Broadway and in modern ballet.
  • 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: Keren
Triple: [Bilen, region, Keren]
Generated description
Keren is a major town in Eritrea known as an important commercial and agricultural center in the Anseba region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Keren
Target entity description: Keren is a major town in Eritrea known as an important commercial and agricultural center in the Anseba region.
  • A. Sharona Katan
    Sharona Katan is an Israeli-born visual artist and the wife of Radiohead guitarist and composer Jonny Greenwood.
  • B. Alona Tal
    Alona Tal is an Israeli-American actress and singer known for her roles in television series such as "Veronica Mars," "Supernatural," and "Hand of God."
  • C. Rachel Dayan
    Rachel Dayan was the wife of prominent Israeli military leader and politician Moshe Dayan.
  • D. Yoni Brenner
    Yoni Brenner is a screenwriter and humorist known for his work on animated films, including contributing to the screenplay of "Rio 2."
  • E. Tamara Geva
    Tamara Geva was a Russian-American dancer and actress known for her early collaborations with choreographer George Balanchine and her influential work on Broadway and in modern ballet.
  • 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_69aed95b3c088190a8f85d19e6070599 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeec1e68f88190941c39221486f6ae completed March 9, 2026, 3:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69b504228220819082e11b316ba79b08 completed March 14, 2026, 6:45 a.m.
NEDg Description generation batch_69b505420de0819086dee340f34a8886 completed March 14, 2026, 6:50 a.m.
NED2 Entity disambiguation (via description) batch_69b5064192a48190a0f95dee872437e0 completed March 14, 2026, 6:54 a.m.
Created at: March 9, 2026, 3:19 p.m.