Triple

T20149957
Position Surface form Disambiguated ID Type / Status
Subject EC Comics E491408 entity
Predicate notableCharacter P1481 FINISHED
Object Crypt-Keeper NE NERFINISHED

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: Crypt-Keeper | Statement: [EC Comics, notableCharacter, Crypt-Keeper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Crypt-Keeper
Context triple: [EC Comics, notableCharacter, Crypt-Keeper]
  • A. Crypt Keeper chosen
    The Crypt Keeper is a ghoulish, pun-loving horror host best known for introducing and narrating macabre stories in the television series "Tales from the Crypt."
  • B. KeePass
    KeePass is a free, open-source password manager that securely stores and organizes passwords in an encrypted local database.
  • C. Orvault
    Orvault is a suburban commune in western France, forming part of the metropolitan area of Nantes in the Loire-Atlantique department.
  • D. Secret Manager
    Secret Manager is a Google Cloud service for securely storing, managing, and accessing sensitive configuration data such as API keys, passwords, and certificates.
  • E. Keychain
    Keychain is Apple's built-in password and credentials manager that securely stores and autofills logins, certificates, and other sensitive information across its devices and apps.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da6265f8f0819080b29c752a574088 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e667a1c5848190975b17ab07251f8b completed April 20, 2026, 5:51 p.m.
Created at: April 11, 2026, 11:33 p.m.