Triple

T12912838
Position Surface form Disambiguated ID Type / Status
Subject Deathstroke E308901 entity
Predicate spouse P13 FINISHED
Object Adeline Kane
Adeline Kane is a skilled military officer and strategist in DC Comics, best known for her complex relationship with the assassin Deathstroke and her role in training and opposing him.
E1010009 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: Adeline Kane | Statement: [Deathstroke, spouse, Adeline Kane]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Adeline Kane
Context triple: [Deathstroke, spouse, Adeline Kane]
  • A. Adeline
    Adeline is the middle name of Frances Adeline Seward, an American abolitionist and the wife of U.S. Secretary of State William H. Seward.
  • B. Adeline
    Adeline is a fictional character from Honoré de Balzac’s novel "Cousin Bette," known as the long-suffering wife of Baron Hulot.
  • C. Adeline
    Adeline is the virtuous and persecuted heroine of Ann Radcliffe’s Gothic novel "The Romance of the Forest."
  • D. Adeline
    Adeline is the given first name of the renowned English modernist writer Virginia Woolf.
  • E. Rachel Kane
    Rachel Kane is a key CIA operative and mission handler in the video game Call of Duty: Black Ops III, guiding and assisting the player throughout much of the campaign.
  • 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: Adeline Kane
Triple: [Deathstroke, spouse, Adeline Kane]
Generated description
Adeline Kane is a skilled military officer and strategist in DC Comics, best known for her complex relationship with the assassin Deathstroke and her role in training and opposing him.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Adeline Kane
Target entity description: Adeline Kane is a skilled military officer and strategist in DC Comics, best known for her complex relationship with the assassin Deathstroke and her role in training and opposing him.
  • A. Adeline
    Adeline is the middle name of Frances Adeline Seward, an American abolitionist and the wife of U.S. Secretary of State William H. Seward.
  • B. Adeline
    Adeline is a fictional character from Honoré de Balzac’s novel "Cousin Bette," known as the long-suffering wife of Baron Hulot.
  • C. Adeline
    Adeline is the virtuous and persecuted heroine of Ann Radcliffe’s Gothic novel "The Romance of the Forest."
  • D. Adeline
    Adeline is the given first name of the renowned English modernist writer Virginia Woolf.
  • E. Rachel Kane
    Rachel Kane is a key CIA operative and mission handler in the video game Call of Duty: Black Ops III, guiding and assisting the player throughout much of the campaign.
  • 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_69d7bdf92b588190acdf2a2291ac4590 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9719f96248190b746f9d4a468560c completed April 10, 2026, 9:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6a56ea03c819093a5b8657e27768e completed May 3, 2026, 1:31 a.m.
NEDg Description generation batch_69f6a68978008190a9d8695b09a8cb3a completed May 3, 2026, 1:36 a.m.
NED2 Entity disambiguation (via description) batch_69f6a8a31264819082c1ce67eaa529cc completed May 3, 2026, 1:45 a.m.
Created at: April 9, 2026, 5:41 p.m.