Triple
T1468821
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chad Mirkin |
E27085
|
entity |
| Predicate | founded |
P104
|
FINISHED |
| Object |
AuraSense, LLC
AuraSense, LLC is a biotechnology company specializing in nanotechnology-based solutions for diagnostics and therapeutics.
|
E99145
|
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: AuraSense, LLC | Statement: [Chad Mirkin, founded, AuraSense, LLC]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AuraSense, LLC Context triple: [Chad Mirkin, founded, AuraSense, LLC]
-
A.
Syntrillium Software
Syntrillium Software was a software company best known for creating the audio editing program Cool Edit, which later evolved into Adobe Audition after Adobe acquired the firm.
-
B.
Cadabra, Inc.
Cadabra, Inc. was the original name of the company that later became Amazon, the multinational e-commerce and technology giant founded by Jeff Bezos.
-
C.
Element AI
Element AI was a Montreal-based artificial intelligence company and research lab known for developing enterprise AI solutions and advancing deep learning research.
-
D.
Zyvex
Zyvex is a pioneering nanotechnology company known for its early work in molecular nanotechnology and advanced manufacturing.
-
E.
Oath Inc.
Oath Inc. was a Verizon-owned digital media and advertising company formed from the merger of AOL and Yahoo.
- 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: AuraSense, LLC Triple: [Chad Mirkin, founded, AuraSense, LLC]
Generated description
AuraSense, LLC is a biotechnology company specializing in nanotechnology-based solutions for diagnostics and therapeutics.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: AuraSense, LLC Target entity description: AuraSense, LLC is a biotechnology company specializing in nanotechnology-based solutions for diagnostics and therapeutics.
-
A.
Syntrillium Software
Syntrillium Software was a software company best known for creating the audio editing program Cool Edit, which later evolved into Adobe Audition after Adobe acquired the firm.
-
B.
Cadabra, Inc.
Cadabra, Inc. was the original name of the company that later became Amazon, the multinational e-commerce and technology giant founded by Jeff Bezos.
-
C.
Element AI
Element AI was a Montreal-based artificial intelligence company and research lab known for developing enterprise AI solutions and advancing deep learning research.
-
D.
Zyvex
chosen
Zyvex is a pioneering nanotechnology company known for its early work in molecular nanotechnology and advanced manufacturing.
-
E.
Oath Inc.
Oath Inc. was a Verizon-owned digital media and advertising company formed from the merger of AOL and Yahoo.
- F. None of above.
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_69a496d25d6881909dbd84f86d763992 |
completed | March 1, 2026, 7:43 p.m. |
| NER | Named-entity recognition | batch_69a4c5d8bb68819095b7b413247ad657 |
completed | March 1, 2026, 11:03 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad0e805fa481908d6428a4e2fb4c4a |
completed | March 8, 2026, 5:52 a.m. |
| NEDg | Description generation | batch_69ad0f0b145c8190b08af9a6a3325c23 |
completed | March 8, 2026, 5:54 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ad0f9380648190b4db1b9c92f37831 |
completed | March 8, 2026, 5:56 a.m. |
Created at: March 1, 2026, 8:01 p.m.