Triple

T13320128
Position Surface form Disambiguated ID Type / Status
Subject AMD Instinct E317291 entity
Predicate supports P516 FINISHED
Object HBM2
HBM2 is a high-bandwidth second-generation stacked memory technology used in advanced GPUs and accelerators to provide very fast, energy-efficient data access.
 E1033643 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: HBM2 | Statement: [AMD Instinct, supports, HBM2]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HBM2
Context triple: [AMD Instinct, supports, HBM2]
  • A. HM-B
    HM-B is the stock ticker symbol for H&M’s publicly traded shares on the Nasdaq Stockholm exchange.
  • B. M2HB
    The M2HB is a heavy-barrel variant of the Browning .50 caliber machine gun, widely used for its durability and sustained fire capability in ground, vehicle, and naval mounts.
  • C. BxM2
    BxM2 is an express bus route in New York City that provides commuter service between the Bronx and Manhattan.
  • D. HM7B
    The HM7B is a European cryogenic rocket engine that powers the upper stages of Ariane launch vehicles, providing precise orbital insertion using liquid hydrogen and liquid oxygen propellants.
  • E. BHB
    BHB is the stock exchange of the Kingdom of Bahrain, providing a regulated marketplace for trading securities and other financial instruments.
  • 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: HBM2
Triple: [AMD Instinct, supports, HBM2]
Generated description
HBM2 is a high-bandwidth second-generation stacked memory technology used in advanced GPUs and accelerators to provide very fast, energy-efficient data access.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HBM2
Target entity description: HBM2 is a high-bandwidth second-generation stacked memory technology used in advanced GPUs and accelerators to provide very fast, energy-efficient data access.
  • A. HM-B
    HM-B is the stock ticker symbol for H&M’s publicly traded shares on the Nasdaq Stockholm exchange.
  • B. M2HB
    The M2HB is a heavy-barrel variant of the Browning .50 caliber machine gun, widely used for its durability and sustained fire capability in ground, vehicle, and naval mounts.
  • C. BxM2
    BxM2 is an express bus route in New York City that provides commuter service between the Bronx and Manhattan.
  • D. HM7B
    The HM7B is a European cryogenic rocket engine that powers the upper stages of Ariane launch vehicles, providing precise orbital insertion using liquid hydrogen and liquid oxygen propellants.
  • E. BHB
    BHB is the stock exchange of the Kingdom of Bahrain, providing a regulated marketplace for trading securities and other financial instruments.
  • 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_69d806b4d62c81908d4ced1665414be5 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d990faa95481908a7fd297959c062e completed April 11, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69f716ee695c81909ffeeb0901ee66c1 completed May 3, 2026, 9:35 a.m.
NEDg Description generation batch_69f717f4d80c8190a1a95c0f2c83c563 completed May 3, 2026, 9:40 a.m.
NED2 Entity disambiguation (via description) batch_69f718b852808190a2a0fb48424bffb0 completed May 3, 2026, 9:43 a.m.
Created at: April 9, 2026, 9:29 p.m.