Triple

T18724863
Position Surface form Disambiguated ID Type / Status
Subject Gil Elbaz E457873 entity
Predicate employer P7 FINISHED
Object Applied Semantics E1339939 NE FINISHED

How this triple was built (2 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: Applied Semantics | Statement: [Gil Elbaz, employer, Applied Semantics]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Applied Semantics
Context triple: [Gil Elbaz, employer, Applied Semantics]
  • A. Applied Semantics chosen
    Applied Semantics was a software company best known for developing the contextual advertising technology that became the foundation of Google AdSense.
  • B. The Establishment of Scientific Semantics
    The Establishment of Scientific Semantics is an influential essay by Alfred Tarski that lays out a rigorous, formal approach to defining truth and meaning in scientific languages.
  • C. Structural Semantics
    Structural Semantics is a seminal work in linguistic theory by Sir John Lyons that systematically analyzes meaning through the structural relationships within language.
  • D. Semantics and Cognition
    Semantics and Cognition is a foundational book in cognitive linguistics that explores how meaning in language is structured and represented in the human mind.
  • E. Semantics and Pragmatics
    Semantics and Pragmatics is a peer-reviewed open-access academic journal focusing on research in linguistic semantics and pragmatics.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d8d393ba9c8190a8b03b04ddbb0a09 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e56d72d2c4819080b0d31860976b5e completed April 20, 2026, 12:04 a.m.
NED1 Entity disambiguation (via context triple) batch_6a054708d7dc8190b85566c17ee67d35 completed May 14, 2026, 3:52 a.m.
Created at: April 10, 2026, 11:50 a.m.