Triple

T21800672
Position Surface form Disambiguated ID Type / Status
Subject Hiroshi Abe E538229 entity
Predicate notableWork P4 FINISHED
Object Dragon Zakura
Dragon Zakura is a popular Japanese manga and television drama series about an unconventional lawyer who helps underachieving students gain admission to the University of Tokyo.
E1502040 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: Dragon Zakura | Statement: [Hiroshi Abe, notableWork, Dragon Zakura]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dragon Zakura
Context triple: [Hiroshi Abe, notableWork, Dragon Zakura]
  • A. Unryu
    Unryu was a World War II-era Imperial Japanese Navy aircraft carrier that served in the Pacific Theater.
  • B. Gishin
    Gishin was an early Japanese Tendai Buddhist monk and scholar who helped establish and systematize the Tendai school following the teachings of his mentor Dengyō Daishi (Saichō).
  • C. Thunder Dragon
    Thunder Dragon is the English rendering of "Druk," the mythical dragon symbol central to Bhutanese national identity and its Drukpa lineage of Tibetan Buddhism.
  • D. Koshun
    Koshun is a music producer known for working on projects associated with the artist Amala.
  • E. Suzaku
    Suzaku was a Japanese X-ray astronomy satellite, developed in collaboration with NASA, that studied high-energy phenomena such as black holes, supernova remnants, and galaxy clusters.
  • 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: Dragon Zakura
Triple: [Hiroshi Abe, notableWork, Dragon Zakura]
Generated description
Dragon Zakura is a popular Japanese manga and television drama series about an unconventional lawyer who helps underachieving students gain admission to the University of Tokyo.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Dragon Zakura
Target entity description: Dragon Zakura is a popular Japanese manga and television drama series about an unconventional lawyer who helps underachieving students gain admission to the University of Tokyo.
  • A. Unryu
    Unryu was a World War II-era Imperial Japanese Navy aircraft carrier that served in the Pacific Theater.
  • B. Gishin
    Gishin was an early Japanese Tendai Buddhist monk and scholar who helped establish and systematize the Tendai school following the teachings of his mentor Dengyō Daishi (Saichō).
  • C. Thunder Dragon
    Thunder Dragon is the English rendering of "Druk," the mythical dragon symbol central to Bhutanese national identity and its Drukpa lineage of Tibetan Buddhism.
  • D. Koshun
    Koshun is a music producer known for working on projects associated with the artist Amala.
  • E. Suzaku
    Suzaku was a Japanese X-ray astronomy satellite, developed in collaboration with NASA, that studied high-energy phenomena such as black holes, supernova remnants, and galaxy clusters.
  • 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_69e0c4733f4081909a86622e7e6d15d2 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f077fede848190b8fe07941d6573d9 completed April 28, 2026, 9:03 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0a3e827ad88190869f3c4797c80891 completed May 17, 2026, 10:17 p.m.
NEDg Description generation batch_6a0a3f4358d48190a88208a55d19a9ef completed May 17, 2026, 10:20 p.m.
NED2 Entity disambiguation (via description) batch_6a0a404206e0819080c640619cd277ab completed May 17, 2026, 10:25 p.m.
Created at: April 16, 2026, 6:53 p.m.