Triple

T31926609
Position Surface form Disambiguated ID Type / Status
Subject First Second Books E815130 entity
Predicate hasPublishedAuthor P4244 FINISHED
Object Mariko Tamaki
Mariko Tamaki is a Canadian writer and comic book creator best known for her award-winning graphic novels exploring queer identity, adolescence, and complex emotional themes.
E2285240 NE FINISHED

How this triple was built (2 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: Mariko Tamaki | Statement: [First Second Books, hasPublishedAuthor, Mariko Tamaki]
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: Mariko Tamaki
Triple: [First Second Books, hasPublishedAuthor, Mariko Tamaki]
Generated description
Mariko Tamaki is a Canadian writer and comic book creator best known for her award-winning graphic novels exploring queer identity, adolescence, and complex emotional themes.

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_69f348f1df848190851bbfb988da3414 completed April 30, 2026, 12:20 p.m.
NER Named-entity recognition batch_69f6b225c0bc8190bdfa4cae44505edf completed May 3, 2026, 2:25 a.m.
NED1 Entity disambiguation (via context triple) batch_6a4560c01e0881909be5002ca9b2707f completed July 1, 2026, 6:47 p.m.
NEDg Description generation batch_6a457025a6188190ac54821ae19cdf5d completed July 1, 2026, 7:53 p.m.
NED2 Entity disambiguation (via description) batch_6a45913132248190935a23be2ece2aa6 completed July 1, 2026, 10:14 p.m.
Created at: May 1, 2026, 12:03 a.m.