Triple

T13479790
Position Surface form Disambiguated ID Type / Status
Subject Kandyan kings E318341 entity
Predicate administrativeDivision P747 FINISHED
Object disavas
Disavas were regional administrative districts in the Kandyan Kingdom of Sri Lanka, each governed by an official responsible for local governance, revenue collection, and military duties.
E1042430 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: disavas | Statement: [Kandyan kings, administrativeDivision, disavas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: disavas
Context triple: [Kandyan kings, administrativeDivision, disavas]
  • A. Diss
    Diss is a historic market town in eastern England known for its picturesque mere and traditional town center.
  • B. Dis
    Dis is the fortified infernal city in Dante Alighieri’s "Inferno," marking the deeper, more grievous circles of Hell.
  • C. Dis
    Dis is an alternate name for Pluto, the Roman god of the underworld and wealth.
  • D. DIS
    DIS is the station code assigned to MTR Disneyland Resort Station, the dedicated railway stop serving Hong Kong Disneyland.
  • E. DIS
    DIS is the stock ticker symbol for The Walt Disney Company, a major global entertainment and media conglomerate traded on the New York Stock Exchange.
  • 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: disavas
Triple: [Kandyan kings, administrativeDivision, disavas]
Generated description
Disavas were regional administrative districts in the Kandyan Kingdom of Sri Lanka, each governed by an official responsible for local governance, revenue collection, and military duties.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: disavas
Target entity description: Disavas were regional administrative districts in the Kandyan Kingdom of Sri Lanka, each governed by an official responsible for local governance, revenue collection, and military duties.
  • A. Diss
    Diss is a historic market town in eastern England known for its picturesque mere and traditional town center.
  • B. Dis
    Dis is an alternate name for Pluto, the Roman god of the underworld and wealth.
  • C. Dis
    Dis is the fortified infernal city in Dante Alighieri’s "Inferno," marking the deeper, more grievous circles of Hell.
  • D. DIS
    DIS is the station code assigned to MTR Disneyland Resort Station, the dedicated railway stop serving Hong Kong Disneyland.
  • E. DIS
    DIS is the stock ticker symbol for The Walt Disney Company, a major global entertainment and media conglomerate traded on the New York Stock Exchange.
  • 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_69d806b6bfec819089222715b2e86c8e completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbaf36c6b08190ba99400600e0b662 completed April 12, 2026, 2:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7463340fc8190b1128bd1d26f91ab completed May 3, 2026, 12:57 p.m.
NEDg Description generation batch_69f747fee42c819097ccfaf01b1bf4da completed May 3, 2026, 1:05 p.m.
NED2 Entity disambiguation (via description) batch_69f748bfc1a481908c3a86018533e45d completed May 3, 2026, 1:08 p.m.
Created at: April 9, 2026, 9:42 p.m.