Triple

T13549636
Position Surface form Disambiguated ID Type / Status
Subject Harry Escott E323607 entity
Predicate notableWork P4 FINISHED
Object Shifty
Shifty is a 2008 British crime drama film about a young drug dealer over the course of a tense 24 hours on a London estate.
 E1047237 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: Shifty | Statement: [Harry Escott, notableWork, Shifty]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Shifty
Context triple: [Harry Escott, notableWork, Shifty]
  • A. Slyly
    Slyly is the colorful, dinosaur-like mascot of Japan’s Hiroshima Toyo Carp professional baseball team, known for its playful antics and fan engagement.
  • B. Shapeshifter
    Shapeshifter is an LF Energy open-source project focused on standardizing and streamlining energy market communications and flexibility services.
  • C. Chingy
    Chingy is an American rapper and actor best known for his early-2000s hit singles like "Right Thurr" and his association with the Disturbing tha Peace label.
  • D. Misfit
    Misfit is a wearable technology and fitness-tracking brand known for its minimalist activity trackers and smartwatches.
  • E. Twist
    "Twist" is a novel by Swedish author Klas Östergren, known for its intricate storytelling and exploration of contemporary Swedish society.
  • 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: Shifty
Triple: [Harry Escott, notableWork, Shifty]
Generated description
Shifty is a 2008 British crime drama film about a young drug dealer over the course of a tense 24 hours on a London estate.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Shifty
Target entity description: Shifty is a 2008 British crime drama film about a young drug dealer over the course of a tense 24 hours on a London estate.
  • A. Slyly
    Slyly is the colorful, dinosaur-like mascot of Japan’s Hiroshima Toyo Carp professional baseball team, known for its playful antics and fan engagement.
  • B. Shapeshifter
    Shapeshifter is an LF Energy open-source project focused on standardizing and streamlining energy market communications and flexibility services.
  • C. Chingy
    Chingy is an American rapper and actor best known for his early-2000s hit singles like "Right Thurr" and his association with the Disturbing tha Peace label.
  • D. Misfit
    Misfit is a wearable technology and fitness-tracking brand known for its minimalist activity trackers and smartwatches.
  • E. Twist
    "Twist" is a novel by Swedish author Klas Östergren, known for its intricate storytelling and exploration of contemporary Swedish society.
  • 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_69d8076776248190bdf0d4fa1f85a5fc completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbafdcecf481909999a173b32a58cd completed April 12, 2026, 2:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69f75da4e19c819090d649b60a2dd410 completed May 3, 2026, 2:37 p.m.
NEDg Description generation batch_69f75ec5101081909652b0c0998b36c8 completed May 3, 2026, 2:42 p.m.
NED2 Entity disambiguation (via description) batch_69f75f4a3b0c81908c0ca0351771953b completed May 3, 2026, 2:44 p.m.
Created at: April 9, 2026, 9:46 p.m.