Triple

T22442410
Position Surface form Disambiguated ID Type / Status
Subject Brian Gleeson E554784 entity
Predicate notableWork P4 FINISHED
Object Standby
"Standby" is a 2014 Irish romantic comedy film in which Brian Gleeson stars as a man who reconnects with an old flame during an unexpected night together in Dublin.
 E1537676 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: Standby | Statement: [Brian Gleeson, notableWork, Standby]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Standby
Context triple: [Brian Gleeson, notableWork, Standby]
  • A. Standby
    "Standby" is a song featured on the album *The Curtain Hits the Cast* by the American indie rock band Low.
  • B. Stand-by
    Stand-by is a French drama film featuring a notable performance by actress Dominique Blanc.
  • C. Standby Reserve
    The Standby Reserve is a category of the U.S. military reserve components consisting of trained individuals who are not in the Selected Reserve or Individual Ready Reserve but can be called to active duty under special circumstances.
  • D. Please Stand By
    Please Stand By is a 2017 comedy-drama film about a young autistic woman who runs away from her group home to submit her Star Trek script to a writing competition.
  • E. Downtime
    "Downtime" is a song featured on the album *Hard II Love* by American R&B artist Usher.
  • 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: Standby
Triple: [Brian Gleeson, notableWork, Standby]
Generated description
"Standby" is a 2014 Irish romantic comedy film in which Brian Gleeson stars as a man who reconnects with an old flame during an unexpected night together in Dublin.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Standby
Target entity description: "Standby" is a 2014 Irish romantic comedy film in which Brian Gleeson stars as a man who reconnects with an old flame during an unexpected night together in Dublin.
  • A. Standby
    "Standby" is a song featured on the album *The Curtain Hits the Cast* by the American indie rock band Low.
  • B. Stand-by
    Stand-by is a French drama film featuring a notable performance by actress Dominique Blanc.
  • C. Standby Reserve
    The Standby Reserve is a category of the U.S. military reserve components consisting of trained individuals who are not in the Selected Reserve or Individual Ready Reserve but can be called to active duty under special circumstances.
  • D. Please Stand By
    Please Stand By is a 2017 comedy-drama film about a young autistic woman who runs away from her group home to submit her Star Trek script to a writing competition.
  • E. Downtime
    "Downtime" is a song featured on the album *Hard II Love* by American R&B artist Usher.
  • 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_69e11e5010e48190ae1e9c9db9697637 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15ae2f7608190b1c1e8bd12ca2162 completed April 29, 2026, 1:12 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b0c71f74881909b8f61494a07dfb2 completed May 18, 2026, 12:56 p.m.
NEDg Description generation batch_6a0b0d5ddfd48190a9ed7dc41035f866 completed May 18, 2026, 1 p.m.
NED2 Entity disambiguation (via description) batch_6a0b0dc247b88190b8c54084c5727941 completed May 18, 2026, 1:01 p.m.
Created at: April 16, 2026, 8:47 p.m.