Triple

T9728898
Position Surface form Disambiguated ID Type / Status
Subject DECsystem-10 E235686 entity
Predicate cpuFamily P11217 FINISHED
Object KS10
KS10 is a later, cost-reduced model of Digital Equipment Corporation’s PDP-10 mainframe line, integrating the CPU onto fewer, more modern hardware modules.
 E817472 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: KS10 | Statement: [DECsystem-10, cpuFamily, KS10]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: KS10
Context triple: [DECsystem-10, cpuFamily, KS10]
  • A. K-10
    K-10 is a state highway in Kansas that serves as a major east–west commuter and connector route in the Kansas City metropolitan area.
  • B. K1
    K1, also known as Masherbrum, is a prominent 7,821-meter peak in the Karakoram range of Pakistan and one of the world’s highest mountains.
  • C. K1
    K1 is the first highly accurate marine chronometer built by Larcum Kendall in the 18th century, famous for its role in improving longitude determination at sea.
  • D. T10
    T10 is a technical committee under INCITS responsible for developing standards for SCSI (Small Computer System Interface) and related storage interfaces.
  • E. SK-105A1
    The SK-105A1 is an upgraded variant of the Austrian SK-105 Kürassier light tank destroyer, featuring improved fire control and combat capabilities.
  • 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: KS10
Triple: [DECsystem-10, cpuFamily, KS10]
Generated description
KS10 is a later, cost-reduced model of Digital Equipment Corporation’s PDP-10 mainframe line, integrating the CPU onto fewer, more modern hardware modules.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: KS10
Target entity description: KS10 is a later, cost-reduced model of Digital Equipment Corporation’s PDP-10 mainframe line, integrating the CPU onto fewer, more modern hardware modules.
  • A. K-10
    K-10 is a state highway in Kansas that serves as a major east–west commuter and connector route in the Kansas City metropolitan area.
  • B. K1
    K1, also known as Masherbrum, is a prominent 7,821-meter peak in the Karakoram range of Pakistan and one of the world’s highest mountains.
  • C. K1
    K1 is the first highly accurate marine chronometer built by Larcum Kendall in the 18th century, famous for its role in improving longitude determination at sea.
  • D. T10
    T10 is a technical committee under INCITS responsible for developing standards for SCSI (Small Computer System Interface) and related storage interfaces.
  • E. SK-105A1
    The SK-105A1 is an upgraded variant of the Austrian SK-105 Kürassier light tank destroyer, featuring improved fire control and combat capabilities.
  • 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_69ca84d0fad481909cdd45aa77416c48 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9eafa3a88190bc62924d94b89cd8 completed April 1, 2026, 10:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69d19fb5f5bc8190ae53bc5c165b5ac7 completed April 4, 2026, 11:33 p.m.
NEDg Description generation batch_69d1a482c0bc81908c3c7ae7c2f19473 completed April 4, 2026, 11:53 p.m.
NED2 Entity disambiguation (via description) batch_69d1a83336308190acb209223da11766 completed April 5, 2026, 12:09 a.m.
Created at: March 30, 2026, 8:21 p.m.