Triple
T13320249
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ATI Technologies |
E317294
|
entity |
| Predicate | product |
P490
|
FINISHED |
| Object |
Rage
Rage is a family of graphics processing units (GPUs) developed by ATI Technologies for accelerating 2D and 3D graphics on personal computers.
|
E1033656
|
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: Rage | Statement: [ATI Technologies, product, Rage]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rage Context triple: [ATI Technologies, product, Rage]
-
A.
Rage
Rage is a nonfiction book by investigative journalist Bob Woodward that examines the Trump presidency through interviews, insider accounts, and analysis of key events.
-
B.
Rage
Rage is a post-apocalyptic first-person shooter video game developed by id Software, known for its advanced graphics technology and vehicular combat elements.
-
C.
Rage
Rage is a psychological horror novel by Stephen King, originally published under the pseudonym Richard Bachman, that follows a troubled high school student who takes his class hostage.
-
D.
Rage
Rage is a Japanese crime drama film featuring Ken Watanabe in a central role, exploring the aftermath of a brutal murder and the corrosive effects of suspicion on human relationships.
-
E.
Rage
Rage is a steel roller coaster at Adventure Island known for its steep drops and intense inversions.
- 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: Rage Triple: [ATI Technologies, product, Rage]
Generated description
Rage is a family of graphics processing units (GPUs) developed by ATI Technologies for accelerating 2D and 3D graphics on personal computers.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Rage Target entity description: Rage is a family of graphics processing units (GPUs) developed by ATI Technologies for accelerating 2D and 3D graphics on personal computers.
-
A.
Rage
Rage is a post-apocalyptic first-person shooter video game developed by id Software, known for its advanced graphics technology and vehicular combat elements.
-
B.
Rage
Rage is a historical adventure novel by Wilbur Smith that continues the saga of the Courtney family against the backdrop of apartheid-era South Africa.
-
C.
Rage
Rage is a steel roller coaster at Adventure Island known for its steep drops and intense inversions.
-
D.
Rage
Rage is a psychological horror novel by Stephen King, originally published under the pseudonym Richard Bachman, that follows a troubled high school student who takes his class hostage.
-
E.
Rage
Rage is a Japanese crime drama film featuring Ken Watanabe in a central role, exploring the aftermath of a brutal murder and the corrosive effects of suspicion on human relationships.
- 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.