Triple

T4254742
Position Surface form Disambiguated ID Type / Status
Subject Taira no Kiyomori E95944 entity
Predicate spouse P13 FINISHED
Object Tokiko
Tokiko, also known as Taira no Tokiko or the Nun of Second Rank, was a prominent noblewoman of the late Heian period and stepmother of Emperor Antoku, influential within the powerful Taira clan.
E430744 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: Tokiko | Statement: [Taira no Kiyomori, spouse, Tokiko]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tokiko
Context triple: [Taira no Kiyomori, spouse, Tokiko]
  • A. Tsutako
    Tsutako is a Japanese given name, most notably borne by Tsutako Nakasone.
  • B. Ibuki
    Ibuki is the nickname of Japan’s Greenhouse Gases Observing Satellite (GOSAT), an Earth observation mission dedicated to monitoring global greenhouse gas concentrations from space.
  • C. Teimei
    Teimei is the posthumous name of the Japanese empress consort of Emperor Taishō, who served as Empress of Japan in the early 20th century.
  • D. Towa
    Towa is a Native American Tanoan language spoken primarily by the Jemez Pueblo people of northern New Mexico.
  • E. Mitaka
    Mitaka is a city in western Tokyo, Japan, known for its residential neighborhoods, parks, and the Ghibli Museum.
  • 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: Tokiko
Triple: [Taira no Kiyomori, spouse, Tokiko]
Generated description
Tokiko, also known as Taira no Tokiko or the Nun of Second Rank, was a prominent noblewoman of the late Heian period and stepmother of Emperor Antoku, influential within the powerful Taira clan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tokiko
Target entity description: Tokiko, also known as Taira no Tokiko or the Nun of Second Rank, was a prominent noblewoman of the late Heian period and stepmother of Emperor Antoku, influential within the powerful Taira clan.
  • A. Tsutako
    Tsutako is a Japanese given name, most notably borne by Tsutako Nakasone.
  • B. Ibuki
    Ibuki is the nickname of Japan’s Greenhouse Gases Observing Satellite (GOSAT), an Earth observation mission dedicated to monitoring global greenhouse gas concentrations from space.
  • C. Teimei
    Teimei is the posthumous name of the Japanese empress consort of Emperor Taishō, who served as Empress of Japan in the early 20th century.
  • D. Towa
    Towa is a Native American Tanoan language spoken primarily by the Jemez Pueblo people of northern New Mexico.
  • E. Mitaka
    Mitaka is a city in western Tokyo, Japan, known for its residential neighborhoods, parks, and the Ghibli Museum.
  • 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_69b3453f759881909b91f01a1e82c036 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b34ec036e8819087d8585170707545 completed March 12, 2026, 11:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5d06299288190bbd8e5f2cfd678d3 completed March 14, 2026, 9:17 p.m.
NEDg Description generation batch_69b5d154965c819099d5f08750239029 completed March 14, 2026, 9:21 p.m.
NED2 Entity disambiguation (via description) batch_69b5d1c2f77c8190942be9d23c2c9f6b completed March 14, 2026, 9:23 p.m.
Created at: March 12, 2026, 11:06 p.m.