Triple

T5829499
Position Surface form Disambiguated ID Type / Status
Subject Daykundi Province E129309 entity
Predicate capital P234 FINISHED
Object Nili
Nili is a small town in central Afghanistan that serves as the administrative and economic hub of Daykundi Province.
 E547890 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: Nili | Statement: [Daykundi Province, capital, Nili]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Nili
Context triple: [Daykundi Province, capital, Nili]
  • A. Tola
    Tola is a minor judge of Israel mentioned in the biblical Book of Judges, known for leading and delivering Israel for 23 years after the time of Abimelech.
  • B. Nansio
    Nansio is the main town and administrative center of Ukerewe Island in Lake Victoria, Tanzania.
  • C. Nicia
    Nicia is a foolish and gullible Florentine lawyer who serves as one of the central comic figures in Niccolò Machiavelli’s play "The Mandrake."
  • D. Nisseni
    Nisseni are the inhabitants or natives of Caltanissetta, a city in central Sicily, Italy.
  • E. Njaba
    Njaba is a local government area in southeastern Nigeria known for its communities within Imo State and its role in local administration and commerce.
  • 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: Nili
Triple: [Daykundi Province, capital, Nili]
Generated description
Nili is a small town in central Afghanistan that serves as the administrative and economic hub of Daykundi Province.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Nili
Target entity description: Nili is a small town in central Afghanistan that serves as the administrative and economic hub of Daykundi Province.
  • A. Tola
    Tola is a minor judge of Israel mentioned in the biblical Book of Judges, known for leading and delivering Israel for 23 years after the time of Abimelech.
  • B. Nansio
    Nansio is the main town and administrative center of Ukerewe Island in Lake Victoria, Tanzania.
  • C. Nicia
    Nicia is a foolish and gullible Florentine lawyer who serves as one of the central comic figures in Niccolò Machiavelli’s play "The Mandrake."
  • D. Nisseni
    Nisseni are the inhabitants or natives of Caltanissetta, a city in central Sicily, Italy.
  • E. Njaba
    Njaba is a local government area in southeastern Nigeria known for its communities within Imo State and its role in local administration and commerce.
  • 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_69c00849d55481908b4f9f5543e0bf6d completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0346905848190a8f541401da05604 completed March 22, 2026, 6:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69c09866fd248190b4248a993051b732 completed March 23, 2026, 1:33 a.m.
NEDg Description generation batch_69c0995672f08190acce2a14266ccf6a completed March 23, 2026, 1:37 a.m.
NED2 Entity disambiguation (via description) batch_69c099fefd6c8190ae1b4480ef133f02 completed March 23, 2026, 1:40 a.m.
Created at: March 22, 2026, 3:54 p.m.