Triple

T11023678
Position Surface form Disambiguated ID Type / Status
Subject Orna Kupferman E260558 entity
Predicate doctoralStudent P167 FINISHED
Object Sharon Shoham
Sharon Shoham is a computer scientist known for her research in formal methods and verification, and for being a doctoral student of Orna Kupferman.
E908131 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: Sharon Shoham | Statement: [Orna Kupferman, doctoralStudent, Sharon Shoham]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sharon Shoham
Context triple: [Orna Kupferman, doctoralStudent, Sharon Shoham]
  • A. Gila Almagor
    Gila Almagor is a renowned Israeli actress, author, and film producer often referred to as the "first lady of Israeli cinema and theatre."
  • B. Orna Kupferman
    Orna Kupferman is an Israeli computer scientist known for her contributions to formal verification, automata theory, and logic in computer science.
  • C. Sarit Kraus
    Sarit Kraus is an Israeli computer scientist known for her influential work in artificial intelligence, multi-agent systems, and human-agent interaction.
  • D. Orna Grumberg
    Orna Grumberg is a prominent computer scientist known for her contributions to formal verification and model checking.
  • E. Daphna Kastner
    Daphna Kastner is a Canadian actress, screenwriter, and director known for her work in independent films.
  • 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: Sharon Shoham
Triple: [Orna Kupferman, doctoralStudent, Sharon Shoham]
Generated description
Sharon Shoham is a computer scientist known for her research in formal methods and verification, and for being a doctoral student of Orna Kupferman.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sharon Shoham
Target entity description: Sharon Shoham is a computer scientist known for her research in formal methods and verification, and for being a doctoral student of Orna Kupferman.
  • A. Gila Almagor
    Gila Almagor is a renowned Israeli actress, author, and film producer often referred to as the "first lady of Israeli cinema and theatre."
  • B. Orna Kupferman
    Orna Kupferman is an Israeli computer scientist known for her contributions to formal verification, automata theory, and logic in computer science.
  • C. Sarit Kraus
    Sarit Kraus is an Israeli computer scientist known for her influential work in artificial intelligence, multi-agent systems, and human-agent interaction.
  • D. Orna Grumberg
    Orna Grumberg is a prominent computer scientist known for her contributions to formal verification and model checking.
  • E. Daphna Kastner
    Daphna Kastner is a Canadian actress, screenwriter, and director known for her work in independent films.
  • 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_69d6aa9687448190b28d353b1b6a610e completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d797be9f148190a3a967bad5947496 completed April 9, 2026, 12:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69e462bd90f48190aa3df8725026a9ba completed April 19, 2026, 5:06 a.m.
NEDg Description generation batch_69e4666f98ac81908b3d3b8a6a8af8c9 completed April 19, 2026, 5:21 a.m.
NED2 Entity disambiguation (via description) batch_69e46c3f28dc8190a521c00151b01fde completed April 19, 2026, 5:46 a.m.
Created at: April 8, 2026, 9:25 p.m.