Triple

T6228017
Position Surface form Disambiguated ID Type / Status
Subject Kalinga E139282 entity
Predicate capital P234 FINISHED
Object Tosali
Tosali was an ancient city that served as a major political and administrative center of the Kalinga kingdom in eastern India.
 E578323 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: Tosali | Statement: [Kalinga, capital, Tosali]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tosali
Context triple: [Kalinga, capital, Tosali]
  • A. Daulida
    Daulida is an alternative name for the ancient Greek town of Daulis in the region of Phocis.
  • B. Selinus
    Selinus was an ancient Greek city on the southwest coast of Sicily, notable for its grand Doric temples and strategic position in the western Greek colonial world.
  • C. Taurisium
    Taurisium is an ancient fortified settlement in present-day North Macedonia, traditionally regarded as the birthplace of the Byzantine emperor Justinian I.
  • D. Menetes
    Menetes is a traditional mountain village on the Greek island of Karpathos, known for its colorful houses, narrow alleys, and panoramic views over the Aegean Sea.
  • E. Menetes
    Menetes is a genus of rodents in the squirrel family, comprising ground-dwelling squirrels native to parts of Asia.
  • 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: Tosali
Triple: [Kalinga, capital, Tosali]
Generated description
Tosali was an ancient city that served as a major political and administrative center of the Kalinga kingdom in eastern India.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tosali
Target entity description: Tosali was an ancient city that served as a major political and administrative center of the Kalinga kingdom in eastern India.
  • A. Daulida
    Daulida is an alternative name for the ancient Greek town of Daulis in the region of Phocis.
  • B. Selinus
    Selinus was an ancient Greek city on the southwest coast of Sicily, notable for its grand Doric temples and strategic position in the western Greek colonial world.
  • C. Taurisium
    Taurisium is an ancient fortified settlement in present-day North Macedonia, traditionally regarded as the birthplace of the Byzantine emperor Justinian I.
  • D. Menetes
    Menetes is a genus of rodents in the squirrel family, comprising ground-dwelling squirrels native to parts of Asia.
  • E. Menetes
    Menetes is a traditional mountain village on the Greek island of Karpathos, known for its colorful houses, narrow alleys, and panoramic views over the Aegean Sea.
  • 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_69c008afd3148190b71e9eaa60420dd1 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c062d686b88190a0e7e38ab52e2d4a completed March 22, 2026, 9:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69c20de16d988190acdec1deba75e06e completed March 24, 2026, 4:06 a.m.
NEDg Description generation batch_69c2141927288190bad4ec024997a45e completed March 24, 2026, 4:33 a.m.
NED2 Entity disambiguation (via description) batch_69c214d7f2d08190bd6dab4da08c97dc completed March 24, 2026, 4:36 a.m.
Created at: March 22, 2026, 4:22 p.m.