Triple

T15017710
Position Surface form Disambiguated ID Type / Status
Subject Closing Time E377998 entity
Predicate starsActor P5563 FINISHED
Object Seroca Davis
Seroca Davis is an actress known for her role in the film "Closing Time."
 E1131386 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: Seroca Davis | Statement: [Closing Time, starsActor, Seroca Davis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Seroca Davis
Context triple: [Closing Time, starsActor, Seroca Davis]
  • A. Marina Jack
    Marina Jack is a popular waterfront dining and marina complex in downtown Sarasota, Florida, known for its boat docks, seafood restaurant, and scenic views of Sarasota Bay.
  • B. Marchioness of Denia
    The Marchioness of Denia is a Spanish noble title historically associated with high-ranking aristocratic families close to the royal court.
  • C. Breezy Lovejoy
    Breezy Lovejoy is the former stage name of American singer, rapper, drummer, and producer Anderson .Paak, used earlier in his music career.
  • D. Cutty Sark
    Cutty Sark is a famous 19th-century British clipper ship preserved as a museum ship and historic landmark in London.
  • E. Gracy
    Gracy is a given name, typically used as a feminine variant of the name Gracie or Grace.
  • 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: Seroca Davis
Triple: [Closing Time, starsActor, Seroca Davis]
Generated description
Seroca Davis is an actress known for her role in the film "Closing Time."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Seroca Davis
Target entity description: Seroca Davis is an actress known for her role in the film "Closing Time."
  • A. Marina Jack
    Marina Jack is a popular waterfront dining and marina complex in downtown Sarasota, Florida, known for its boat docks, seafood restaurant, and scenic views of Sarasota Bay.
  • B. Marchioness of Denia
    The Marchioness of Denia is a Spanish noble title historically associated with high-ranking aristocratic families close to the royal court.
  • C. Breezy Lovejoy
    Breezy Lovejoy is the former stage name of American singer, rapper, drummer, and producer Anderson .Paak, used earlier in his music career.
  • D. Cutty Sark
    Cutty Sark is a famous 19th-century British clipper ship preserved as a museum ship and historic landmark in London.
  • E. Gracy
    Gracy is a given name, typically used as a feminine variant of the name Gracie or Grace.
  • 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_69d85cd3a3c881908c71fc424d459c17 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded7633fcc8190b2231f43252bc46f completed April 15, 2026, 12:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe96ae110c8190a0555590b9ddb36a completed May 9, 2026, 2:06 a.m.
NEDg Description generation batch_69fe97c0a3688190a9f55376a1d7ad87 completed May 9, 2026, 2:11 a.m.
NED2 Entity disambiguation (via description) batch_69fe985cec608190888733cdc5bd71ea completed May 9, 2026, 2:13 a.m.
Created at: April 10, 2026, 2:55 a.m.