Triple

T27582040
Position Surface form Disambiguated ID Type / Status
Subject IBM 3274 control unit E699607 entity
Predicate predecessor P97 FINISHED
Object IBM 3271 control unit
The IBM 3271 control unit was an early mainframe terminal controller used to manage and connect IBM 3270-series display terminals and printers to host computers in data processing environments.
E1780316 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: IBM 3271 control unit | Statement: [IBM 3274 control unit, predecessor, IBM 3271 control unit]
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: IBM 3271 control unit
Triple: [IBM 3274 control unit, predecessor, IBM 3271 control unit]
Generated description
The IBM 3271 control unit was an early mainframe terminal controller used to manage and connect IBM 3270-series display terminals and printers to host computers in data processing environments.

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_69ef6a4cb8b881909b3a8d630fd89df2 completed April 27, 2026, 1:53 p.m.
NER Named-entity recognition batch_69f63016cc1481908862c906df769a43 completed May 2, 2026, 5:10 p.m.
NED1 Entity disambiguation (via context triple) batch_6a12d0d7aa508190a812d773ae6130fb completed May 24, 2026, 10:20 a.m.
NEDg Description generation batch_6a12d1a671948190add200d3ab2db641 completed May 24, 2026, 10:23 a.m.
NED2 Entity disambiguation (via description) batch_6a12d2747f6881909aa2a5b0c389a494 completed May 24, 2026, 10:27 a.m.
Created at: April 27, 2026, 2:03 p.m.