Triple
T962260
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steve Chen |
E20759
|
entity |
| Predicate | founded |
P104
|
FINISHED |
| Object |
Nom.com
Nom.com was a live video streaming and social platform focused on food and cooking, co-founded by YouTube co-founder Steve Chen.
|
E113109
|
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: Nom.com | Statement: [Steve Chen, founded, Nom.com]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nom.com Context triple: [Steve Chen, founded, Nom.com]
-
A.
Nome
Nome is a remote coastal city in western Alaska known historically for its gold rush heritage and as a key transportation and supply hub on the Bering Sea.
-
B.
Norid
Norid is the Norwegian registry responsible for administering the country’s .no top-level internet domain.
-
C.
Nama
Nama is a Khoe language spoken primarily by the Nama people in Namibia and neighboring regions of southern Africa.
-
D.
NAM
NAM is the commonly used abbreviation for the Non-Aligned Movement, an international grouping of states that sought to remain independent from major power blocs during the Cold War and beyond.
-
E.
NAM
NAM is the commonly used acronym for the National Academy of Medicine, a leading U.S. nonprofit institution that provides expert advice on health, medicine, and biomedical science.
- 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: Nom.com Triple: [Steve Chen, founded, Nom.com]
Generated description
Nom.com was a live video streaming and social platform focused on food and cooking, co-founded by YouTube co-founder Steve Chen.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Nom.com Target entity description: Nom.com was a live video streaming and social platform focused on food and cooking, co-founded by YouTube co-founder Steve Chen.
-
A.
Nome
Nome is a remote coastal city in western Alaska known historically for its gold rush heritage and as a key transportation and supply hub on the Bering Sea.
-
B.
Norid
Norid is the Norwegian registry responsible for administering the country’s .no top-level internet domain.
-
C.
Nama
Nama is a Khoe language spoken primarily by the Nama people in Namibia and neighboring regions of southern Africa.
-
D.
NAM
NAM is the commonly used abbreviation for the Non-Aligned Movement, an international grouping of states that sought to remain independent from major power blocs during the Cold War and beyond.
-
E.
NAM
NAM is the commonly used acronym for the National Academy of Medicine, a leading U.S. nonprofit institution that provides expert advice on health, medicine, and biomedical science.
- 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_69a493b21f2881908132dcf45dcd2f36 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4b415ac688190bbcef455935a3116 |
completed | March 1, 2026, 9:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac11a6107481909b152291a73958d3 |
completed | March 7, 2026, 11:53 a.m. |
| NEDg | Description generation | batch_69ac12c5978481909be2d6e1ce85acd5 |
completed | March 7, 2026, 11:57 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ac132f09448190b5f789f90328f81f |
completed | March 7, 2026, 11:59 a.m. |
Created at: March 1, 2026, 7:40 p.m.