Triple
T7387571
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Acer |
E170419
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object |
Carolyn Yeh
Carolyn Yeh is an entrepreneur best known as a founder of the technology company Acer.
|
E660935
|
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: Carolyn Yeh | Statement: [Acer, foundedBy, Carolyn Yeh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carolyn Yeh Context triple: [Acer, foundedBy, Carolyn Yeh]
-
A.
Carolyn Choa
Carolyn Choa is a Hong Kong–born choreographer, dancer, and director known for her work in film, opera, and theatre, as well as for her collaborations with acclaimed director Anthony Minghella.
-
B.
Yvonne Chu
Yvonne Chu is the wife of Nobel Prize–winning physicist and former U.S. Secretary of Energy Steven Chu.
-
C.
Lori Huang
Lori Huang is the wife of NVIDIA co-founder and CEO Jensen Huang and is known for her low public profile despite her connection to the prominent tech executive.
-
D.
Rachel Fong
Rachel Fong is a researcher in machine learning and reinforcement learning, known for her work on the Hindsight Experience Replay technique.
-
E.
Brenda Hsueh
Brenda Hsueh is a Canadian screenwriter and producer known for her work in television comedy and animation, including contributing to major studio projects.
- 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: Carolyn Yeh Triple: [Acer, foundedBy, Carolyn Yeh]
Generated description
Carolyn Yeh is an entrepreneur best known as a founder of the technology company Acer.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Carolyn Yeh Target entity description: Carolyn Yeh is an entrepreneur best known as a founder of the technology company Acer.
-
A.
Carolyn Choa
Carolyn Choa is a Hong Kong–born choreographer, dancer, and director known for her work in film, opera, and theatre, as well as for her collaborations with acclaimed director Anthony Minghella.
-
B.
Yvonne Chu
Yvonne Chu is the wife of Nobel Prize–winning physicist and former U.S. Secretary of Energy Steven Chu.
-
C.
Lori Huang
Lori Huang is the wife of NVIDIA co-founder and CEO Jensen Huang and is known for her low public profile despite her connection to the prominent tech executive.
-
D.
Rachel Fong
Rachel Fong is a researcher in machine learning and reinforcement learning, known for her work on the Hindsight Experience Replay technique.
-
E.
Brenda Hsueh
Brenda Hsueh is a Canadian screenwriter and producer known for her work in television comedy and animation, including contributing to major studio projects.
- 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_69c68a5e2c9081909e713ce866e0060a |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f1f2bac481908ac74069182a4ce4 |
completed | March 27, 2026, 9:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c802e56fb48190976612d2a94d6ee5 |
completed | March 28, 2026, 4:33 p.m. |
| NEDg | Description generation | batch_69c803707cec8190bb474c959ef93d48 |
completed | March 28, 2026, 4:36 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c803ed9ec4819090a9481954060769 |
completed | March 28, 2026, 4:38 p.m. |
Created at: March 27, 2026, 3:08 p.m.