Triple

T12146063
Position Surface form Disambiguated ID Type / Status
Subject Phyllis Haver E289324 entity
Predicate familyName P18 FINISHED
Object Haver
Haver is the surname of American silent film actress Phyllis Haver, known for her roles in early Hollywood comedies and dramas.
 E965110 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: Haver | Statement: [Phyllis Haver, familyName, Haver]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Haver
Context triple: [Phyllis Haver, familyName, Haver]
  • A. Hamren
    Hamren is a town in the Indian state of Assam that serves as the main administrative and service center for the surrounding West Karbi Anglong region.
  • B. Haravgi
    Haravgi is a Cypriot newspaper that serves as the main press organ of the left-wing Progressive Party of Working People (AKEL).
  • C. Hartis
    Hartis is a prominent Somali clan family that forms one of the major lineages within the broader Somali clan system.
  • D. Hasle
    Hasle is a small coastal town on the Danish island of Bornholm, known for its historic harbor, smoked herring, and scenic Baltic Sea surroundings.
  • E. Havah
    Havah is a transliteration of the Hebrew name for Eve, the first woman in the biblical creation narrative.
  • 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: Haver
Triple: [Phyllis Haver, familyName, Haver]
Generated description
Haver is the surname of American silent film actress Phyllis Haver, known for her roles in early Hollywood comedies and dramas.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Haver
Target entity description: Haver is the surname of American silent film actress Phyllis Haver, known for her roles in early Hollywood comedies and dramas.
  • A. Hamren
    Hamren is a town in the Indian state of Assam that serves as the main administrative and service center for the surrounding West Karbi Anglong region.
  • B. Haravgi
    Haravgi is a Cypriot newspaper that serves as the main press organ of the left-wing Progressive Party of Working People (AKEL).
  • C. Hartis
    Hartis is a prominent Somali clan family that forms one of the major lineages within the broader Somali clan system.
  • D. Hasle
    Hasle is a small coastal town on the Danish island of Bornholm, known for its historic harbor, smoked herring, and scenic Baltic Sea surroundings.
  • E. Havah
    Havah is a transliteration of the Hebrew name for Eve, the first woman in the biblical creation narrative.
  • 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_69d6ab4c6710819097a9d228382dde43 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d915ac2ebc81909155f9b2fb4a2252 completed April 10, 2026, 3:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69f5f696ec648190aa43655ac8a2b312 completed May 2, 2026, 1:05 p.m.
NEDg Description generation batch_69f600b7385881909ddb86a1d39ff5d4 completed May 2, 2026, 1:48 p.m.
NED2 Entity disambiguation (via description) batch_69f601e7f3b0819098a2245b9f9316b9 completed May 2, 2026, 1:53 p.m.
Created at: April 8, 2026, 9:49 p.m.