Triple

T1839894
Position Surface form Disambiguated ID Type / Status
Subject Kiss Me Deadly E41150 entity
Predicate character P662 FINISHED
Object 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."
E211461 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: Velda | Statement: [Kiss Me Deadly, character, Velda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Velda
Context triple: [Kiss Me Deadly, character, Velda]
  • A. Freirina
    Freirina is a small town and commune in northern Chile known for its agricultural activity and historic architecture within the Atacama Region.
  • B. Huelén
    Huelén is the former indigenous name for Cerro Santa Lucía, a historic hill and urban park in central Santiago, Chile.
  • C. Valbo
    Valbo is a locality in Gävleborg County, Sweden, known as the hometown of NHL ice hockey star Nicklas Bäckström.
  • D. Velkua
    Velkua is a former island municipality in southwestern Finland known for its coastal archipelago landscape in the Baltic Sea.
  • E. Tynaarlo
    Tynaarlo is a municipality in the northeastern Netherlands known for its rural character and location between the cities of Groningen and Assen.
  • 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: Velda
Triple: [Kiss Me Deadly, character, Velda]
Generated description
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."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Velda
Target entity description: 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."
  • A. Freirina
    Freirina is a small town and commune in northern Chile known for its agricultural activity and historic architecture within the Atacama Region.
  • B. Huelén
    Huelén is the former indigenous name for Cerro Santa Lucía, a historic hill and urban park in central Santiago, Chile.
  • C. Valbo
    Valbo is a locality in Gävleborg County, Sweden, known as the hometown of NHL ice hockey star Nicklas Bäckström.
  • D. Velkua
    Velkua is a former island municipality in southwestern Finland known for its coastal archipelago landscape in the Baltic Sea.
  • E. Tynaarlo
    Tynaarlo is a municipality in the northeastern Netherlands known for its rural character and location between the cities of Groningen and Assen.
  • 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_69a88647f9388190909bc36e795bdaec completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb03b3eb08190ae68d8476fc89c7f completed March 7, 2026, 4:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69adead8e9148190b7cba0f325dc58c4 completed March 8, 2026, 9:32 p.m.
NEDg Description generation batch_69adeb6e8fe08190a4732d42aa15ee8e completed March 8, 2026, 9:34 p.m.
NED2 Entity disambiguation (via description) batch_69adebea03a08190bd055e3e6460b5f4 completed March 8, 2026, 9:36 p.m.
Created at: March 4, 2026, 7:33 p.m.