Triple

T9968553
Position Surface form Disambiguated ID Type / Status
Subject Arthur Curry E195743 entity
Predicate family P566 FINISHED
Object Atlanna E746331 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: Atlanna | Statement: [Arthur Curry, family, Atlanna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Atlanna
Context triple: [Arthur Curry, family, Atlanna]
  • A. Atlanna chosen
    Atlanna is the Atlantean queen and mother of Aquaman, known for bridging the worlds of land and sea in DC's Aquaman films.
  • B. Everina
    Everina Wollstonecraft was an 18th-century English governess and writer, best known as the younger sister of feminist philosopher Mary Wollstonecraft.
  • C. Altilia
    Altilia is the modern Italian village that encompasses the archaeological remains of the ancient Roman town of Saepinum in the Molise region.
  • D. Lelylaan
    Lelylaan is a transport hub and railway/metro station in Amsterdam’s Nieuw-West district, connecting metro, train, tram, and bus services.
  • E. Velda
    Velda is the loyal and resourceful secretary and love interest of private investigator Mike Hammer in the hardboiled crime novel and film "Kiss Me Deadly."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca82ebd1288190912f9e4482d1fa35 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb7b683ac8190ac97bd775a860d29 completed April 2, 2026, 12:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69d23db701b881909bb986a32df4349b completed April 5, 2026, 10:47 a.m.
Created at: March 30, 2026, 8:47 p.m.