Triple

T31946146
Position Surface form Disambiguated ID Type / Status
Subject AMD TeraScale architecture E815655 entity
Predicate usedIn P98 FINISHED
Object Radeon HD 6970
Radeon HD 6970 is a high-end AMD graphics card from the Radeon HD 6000 series, designed for gaming and enthusiast desktop PCs with support for DirectX 11-era features.
E1990720 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: Radeon HD 6970 | Statement: [AMD TeraScale architecture, usedIn, Radeon HD 6970]
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: Radeon HD 6970
Triple: [AMD TeraScale architecture, usedIn, Radeon HD 6970]
Generated description
Radeon HD 6970 is a high-end AMD graphics card from the Radeon HD 6000 series, designed for gaming and enthusiast desktop PCs with support for DirectX 11-era features.

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_69f348f42d188190a33fc8d20ec50517 completed April 30, 2026, 12:20 p.m.
NER Named-entity recognition batch_69f6b27930d881909d5bef056bf5e7e5 completed May 3, 2026, 2:27 a.m.
NED1 Entity disambiguation (via context triple) batch_6a2eddcd3cac8190a10498d6cb94297c completed June 14, 2026, 4:58 p.m.
NEDg Description generation batch_6a2edea2a2e8819087f7ba8685391436 completed June 14, 2026, 5:02 p.m.
NED2 Entity disambiguation (via description) batch_6a2edf61f11081909a3eb6468d916240 completed June 14, 2026, 5:05 p.m.
Created at: May 1, 2026, 12:06 a.m.