Triple

T20698368
Position Surface form Disambiguated ID Type / Status
Subject Ms. Marvel (Carol Danvers) E508712 entity
Predicate aliases P39 FINISHED
Object Warbird
Warbird is a superhero identity used by Carol Danvers during a period of her Marvel Comics history when she operated as an Avenger under a new codename.
E1446039 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: Warbird | Statement: [Ms. Marvel (Carol Danvers), aliases, Warbird]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Warbird
Context triple: [Ms. Marvel (Carol Danvers), aliases, Warbird]
  • A. Airacomet
    Airacomet is the nickname of the Bell P-59, the first American jet fighter aircraft developed during World War II.
  • B. Aviators
    Aviators is a Minor League Baseball team based in the Las Vegas area, serving as the Triple-A affiliate of the Oakland Athletics.
  • C. Skyhawk
    Skyhawk is the athletic mascot representing the University of Tennessee at Martin’s sports teams.
  • D. Skyhawk
    Skyhawk is the athletic mascot representing Navajo Technical University’s sports teams and school spirit.
  • E. Big Wing
    Big Wing was a World War II Royal Air Force fighter tactic that involved massing large formations of fighters to intercept enemy raids, most notably during the Battle of Britain.
  • 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: Warbird
Triple: [Ms. Marvel (Carol Danvers), aliases, Warbird]
Generated description
Warbird is a superhero identity used by Carol Danvers during a period of her Marvel Comics history when she operated as an Avenger under a new codename.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Warbird
Target entity description: Warbird is a superhero identity used by Carol Danvers during a period of her Marvel Comics history when she operated as an Avenger under a new codename.
  • A. Airacomet
    Airacomet is the nickname of the Bell P-59, the first American jet fighter aircraft developed during World War II.
  • B. Aviators
    Aviators is a Minor League Baseball team based in the Las Vegas area, serving as the Triple-A affiliate of the Oakland Athletics.
  • C. Skyhawk
    Skyhawk is the athletic mascot representing the University of Tennessee at Martin’s sports teams.
  • D. Skyhawk
    Skyhawk is the athletic mascot representing Navajo Technical University’s sports teams and school spirit.
  • E. Big Wing
    Big Wing was a World War II Royal Air Force fighter tactic that involved massing large formations of fighters to intercept enemy raids, most notably during the Battle of Britain.
  • 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_69e0b4c2b2a481909e31e9cb8f81ab55 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6c113e4cc8190aabc11e3f2530e32 completed April 21, 2026, 12:13 a.m.
NED1 Entity disambiguation (via context triple) batch_6a08d7eb1d4081908ff9c44ee5f0e20b completed May 16, 2026, 8:47 p.m.
NEDg Description generation batch_6a08db94ca14819092fd6d767fefc342 completed May 16, 2026, 9:03 p.m.
NED2 Entity disambiguation (via description) batch_6a08dc141c648190bf98aa04adae4170 completed May 16, 2026, 9:05 p.m.
Created at: April 16, 2026, 12:11 p.m.