Triple

T6462026
Position Surface form Disambiguated ID Type / Status
Subject King Warrior E142143 entity
Predicate shortName P43 FINISHED
Object King
King is a professional esports player best known for competing under the handle "King" in games such as League of Legends.
E594313 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: King | Statement: [King Warrior, shortName, King]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: King
Context triple: [King Warrior, shortName, King]
  • A. King
    King is a public transit stop commonly associated with King Street, likely serving as a key access point along that corridor.
  • B. King
    The King is the reigning male monarch who serves as the head of state of the United Kingdom within its constitutional monarchy system.
  • C. King
    King is a township in the Regional Municipality of York in Ontario, Canada, known for its rural landscapes, rolling hills, and equestrian farms within the Greater Toronto Area.
  • D. King
    The King of Norway is the constitutional monarch and ceremonial head of state in Norway’s parliamentary system.
  • E. King
    King is a prominent video game company best known for creating the massively popular mobile puzzle game Candy Crush Saga.
  • 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: King
Triple: [King Warrior, shortName, King]
Generated description
King is a professional esports player best known for competing under the handle "King" in games such as League of Legends.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: King
Target entity description: King is a professional esports player best known for competing under the handle "King" in games such as League of Legends.
  • A. King
    King is a prominent video game company best known for creating the massively popular mobile puzzle game Candy Crush Saga.
  • B. King
    King is a masculine given name, historically associated with leadership or nobility and occasionally used as a first name in English-speaking countries.
  • C. King
    King is a regal title traditionally denoting a male sovereign ruler of a kingdom, often associated with supreme authority and hereditary monarchy.
  • D. King
    The King is the reigning male monarch who serves as the head of state of the United Kingdom within its constitutional monarchy system.
  • E. King
    King is a common English surname borne by numerous notable figures, including civil rights leader Martin Luther King Jr.
  • 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_69c008d2f91c8190a8178767a35e08fc completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c069f683248190a58beb60f009eafb completed March 22, 2026, 10:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c64be4e6888190a685f447e9950163 completed March 27, 2026, 9:20 a.m.
NEDg Description generation batch_69c64e4413f481908561a86bc9a9b0b2 completed March 27, 2026, 9:30 a.m.
NED2 Entity disambiguation (via description) batch_69c64ec0d40881908fda2e994f0f6ed5 completed March 27, 2026, 9:32 a.m.
Created at: March 22, 2026, 4:49 p.m.