Triple

T1637105
Position Surface form Disambiguated ID Type / Status
Subject Romancing the Stone E35380 entity
Predicate containsCharacter P5716 FINISHED
Object Ira
Ira is a supporting character in the 1984 adventure-romance film "Romancing the Stone," involved in the story’s treasure-hunting and kidnapping plot.
 E183555 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: Ira | Statement: [Romancing the Stone, containsCharacter, Ira]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ira
Context triple: [Romancing the Stone, containsCharacter, Ira]
  • A. Dana
    Dana is a feminine given name commonly used in various cultures, including Czech, English, and Hebrew-speaking communities.
  • B. Dana
    Dana is a scientific work or authority that provides the formal description and classification of Antarctic krill.
  • C. Mahlon
    Mahlon is a minor biblical figure in the Book of Ruth, known as one of Naomi’s sons and the first husband of Ruth.
  • D. Niles
    Niles is a historic former town in California, now a district of Fremont, known for its early silent film industry and railroad heritage.
  • E. Arvin
    Arvin is a small agricultural city in Southern California’s San Joaquin Valley, known for its farming economy and diverse rural community.
  • 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: Ira
Triple: [Romancing the Stone, containsCharacter, Ira]
Generated description
Ira is a supporting character in the 1984 adventure-romance film "Romancing the Stone," involved in the story’s treasure-hunting and kidnapping plot.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ira
Target entity description: Ira is a supporting character in the 1984 adventure-romance film "Romancing the Stone," involved in the story’s treasure-hunting and kidnapping plot.
  • A. Dana
    Dana is a feminine given name commonly used in various cultures, including Czech, English, and Hebrew-speaking communities.
  • B. Dana
    Dana is a scientific work or authority that provides the formal description and classification of Antarctic krill.
  • C. Mahlon
    Mahlon is a minor biblical figure in the Book of Ruth, known as one of Naomi’s sons and the first husband of Ruth.
  • D. Niles
    Niles is a historic former town in California, now a district of Fremont, known for its early silent film industry and railroad heritage.
  • E. Arvin
    Arvin is a small agricultural city in Southern California’s San Joaquin Valley, known for its farming economy and diverse rural community.
  • 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_69a886036bc081909ff5de16dbe5e8ea completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a90a192d588190bbfa4693ed787c05 completed March 5, 2026, 4:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad58ddfdbc819096578412818fdfbf completed March 8, 2026, 11:09 a.m.
NEDg Description generation batch_69ad595841788190a97bbfded30110c5 completed March 8, 2026, 11:11 a.m.
NED2 Entity disambiguation (via description) batch_69ad59f329cc8190814de211fb00c7b8 completed March 8, 2026, 11:13 a.m.
Created at: March 4, 2026, 7:28 p.m.