Triple

T17964891
Position Surface form Disambiguated ID Type / Status
Subject Tessa Ross E449176 entity
Predicate notableWork P4 FINISHED
Object Brooklyn
Brooklyn is a 2015 romantic drama film about a young Irish woman who emigrates to 1950s New York, acclaimed for its performances and adaptation of Colm Tóibín’s novel.
 E911455 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: Brooklyn | Statement: [Tessa Ross, notableWork, Brooklyn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Brooklyn
Context triple: [Tessa Ross, notableWork, Brooklyn]
  • A. Brooklyn
    Brooklyn is a populous and culturally diverse borough of New York City known for its distinct neighborhoods, arts scene, and iconic landmarks like the Brooklyn Bridge.
  • B. Brooklyn
    Brooklyn is a residential suburb within the Milnerton area of Cape Town, South Africa.
  • C. Brooklyn
    Brooklyn is a small city in Poweshiek County, Iowa, known for its collection of flags from around the world and its nickname "Community of Flags."
  • D. Brooklyn
    Brooklyn is a red-skinned, beaked gargoyle and the second-in-command of the Manhattan Clan in the animated television series "Gargoyles."
  • E. Brooklyn
    Brooklyn is a residential suburb within the coastal city of Burnie in Tasmania, Australia.
  • 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: Brooklyn
Triple: [Tessa Ross, notableWork, Brooklyn]
Generated description
Brooklyn is a 2015 romantic drama film about a young Irish woman who emigrates to 1950s New York, acclaimed for its performances and adaptation of Colm Tóibín’s novel.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Brooklyn
Target entity description: Brooklyn is a 2015 romantic drama film about a young Irish woman who emigrates to 1950s New York, acclaimed for its performances and adaptation of Colm Tóibín’s novel.
  • A. Brooklyn chosen
    "Brooklyn" is a 2015 period drama film about a young Irish woman who emigrates to New York in the 1950s and must choose between her new life in America and her roots in Ireland.
  • B. Brooklyn
    Brooklyn is a populous and culturally diverse borough of New York City known for its distinct neighborhoods, arts scene, and iconic landmarks like the Brooklyn Bridge.
  • C. Brooklyn
    Brooklyn is a residential suburb within the Milnerton area of Cape Town, South Africa.
  • D. Brooklyn
    Brooklyn is a residential suburb of Wellington, New Zealand, known for its hilltop wind turbine, views over the city, and access to nearby parks and walking tracks.
  • E. Brooklyn
    Brooklyn is a residential suburb within the coastal city of Burnie in Tasmania, Australia.
  • F. None of above.

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_69d8b9f9927c8190a006110c8b996e61 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4b136e4088190ac97fd92dc84a4b9 completed April 19, 2026, 10:40 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0397ebabcc81908e6cfe983afcb943 completed May 12, 2026, 9:13 p.m.
NEDg Description generation batch_6a0399364d988190a457415c9c64a68d completed May 12, 2026, 9:18 p.m.
NED2 Entity disambiguation (via description) batch_6a0399e221308190988e728b9efb0141 completed May 12, 2026, 9:21 p.m.
Created at: April 10, 2026, 10:22 a.m.