Triple

T13844379
Position Surface form Disambiguated ID Type / Status
Subject Dov Frohman E332753 entity
Predicate employer P7 FINISHED
Object Intel E4435 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: Intel | Statement: [Dov Frohman, employer, Intel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Intel
Context triple: [Dov Frohman, employer, Intel]
  • A. Intel Corporation chosen
    Intel Corporation is a leading American semiconductor company best known for designing and manufacturing microprocessors that power the majority of the world’s personal computers and servers.
  • B. VIA Technologies
    VIA Technologies is a Taiwanese fabless semiconductor company best known for designing low-power x86-compatible processors and chipsets for PCs and embedded systems.
  • C. Intel processors
    Intel processors are a broad line of microprocessors from Intel Corporation that power a wide range of computing devices, from budget PCs to high-performance servers and workstations.
  • D. AMD
    AMD is the official three-letter currency code for the Armenian dram, the national currency of Armenia.
  • E. AMD processors
    AMD processors are a family of CPUs and APUs from Advanced Micro Devices known for offering strong multi-core performance and competitive pricing across desktops, laptops, and mobile devices.
  • 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_69d81c5ba13c8190839315f54768acfd completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02b1a25c8190a9f85ba43c421188 completed April 14, 2026, 9:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7b8f87c188190b90faf7678cb9ad4 completed May 3, 2026, 9:07 p.m.
Created at: April 9, 2026, 10:13 p.m.