Triple

T14335899
Position Surface form Disambiguated ID Type / Status
Subject Darshan Upadhyaya E355465 entity
Predicate inGameName P113836 FINISHED
Object ZionSpartan
ZionSpartan is the in-game alias of Darshan Upadhyaya, a professional League of Legends top laner known for his time on teams like Counter Logic Gaming.
E1092951 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: ZionSpartan | Statement: [Darshan Upadhyaya, inGameName, ZionSpartan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ZionSpartan
Context triple: [Darshan Upadhyaya, inGameName, ZionSpartan]
  • A. Zay
    Zay is a lesser-known Ethiopian Semitic language spoken by the Zay people, primarily around Lake Ziway in central Ethiopia.
  • B. Zay
    Zay is the surname of Jean Zay, a notable French politician and Minister of National Education and Fine Arts during the 1930s.
  • C. Zaka
    Zaka is a rural district and administrative center located in southeastern Zimbabwe.
  • D. Spartali
    Spartali is the surname of Marie Spartali Stillman, a prominent 19th-century British Pre-Raphaelite painter of Greek descent.
  • E. Zas
    Zas is the highest mountain on the Greek island of Naxos in the Cyclades, known for its prominent peak and hiking trails.
  • 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: ZionSpartan
Triple: [Darshan Upadhyaya, inGameName, ZionSpartan]
Generated description
ZionSpartan is the in-game alias of Darshan Upadhyaya, a professional League of Legends top laner known for his time on teams like Counter Logic Gaming.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: ZionSpartan
Target entity description: ZionSpartan is the in-game alias of Darshan Upadhyaya, a professional League of Legends top laner known for his time on teams like Counter Logic Gaming.
  • A. Zay
    Zay is the surname of Jean Zay, a notable French politician and Minister of National Education and Fine Arts during the 1930s.
  • B. Zay
    Zay is a lesser-known Ethiopian Semitic language spoken by the Zay people, primarily around Lake Ziway in central Ethiopia.
  • C. Zaka
    Zaka is a rural district and administrative center located in southeastern Zimbabwe.
  • D. Spartali
    Spartali is the surname of Marie Spartali Stillman, a prominent 19th-century British Pre-Raphaelite painter of Greek descent.
  • E. Zas
    Zas is the highest mountain on the Greek island of Naxos in the Cyclades, known for its prominent peak and hiking trails.
  • 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_69d8278fa2108190bc0d0e7939c1eb03 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8c20d2148190bb534bef338e871d completed April 14, 2026, 6:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd46986758819088750150ad47bae1 completed May 8, 2026, 2:12 a.m.
NEDg Description generation batch_69fd47a9b5008190a15de0f427771505 completed May 8, 2026, 2:17 a.m.
NED2 Entity disambiguation (via description) batch_69fd4828f44c81908903d1391c83cc60 completed May 8, 2026, 2:19 a.m.
Created at: April 10, 2026, 1:14 a.m.