Triple
T4707026
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeff Wu |
E104412
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | GPT-2 |
E18339
|
NE FINISHED |
How this triple was built (2 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: GPT-2 | Statement: [Jeff Wu, notableWork, GPT-2]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GPT-2 Context triple: [Jeff Wu, notableWork, GPT-2]
-
A.
GPT-2
chosen
GPT-2 is a large transformer-based language model known for generating coherent, human-like text and sparking widespread discussion about the implications of advanced AI text generation.
-
B.
GPT-3
GPT-3 is a large-scale autoregressive language model known for generating human-like text and performing a wide range of natural language tasks with minimal fine-tuning.
-
C.
GPT-Neo
GPT-Neo is an open-source family of autoregressive language models developed by EleutherAI as a free alternative to OpenAI’s GPT-3.
-
D.
GPT
GPT is a family of large language models developed by OpenAI that can understand and generate human-like text for a wide range of tasks.
-
E.
LLaMA
LLaMA is a family of large language models developed by Meta AI, designed for efficient training and inference across a range of natural language processing tasks.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69bd43eac3c08190af7e4020c6c3704c |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd63e9f0b88190820aa7fba2f91b6e |
completed | March 20, 2026, 3:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be106d1fc08190808c19025c6f37c4 |
completed | March 21, 2026, 3:28 a.m. |
Created at: March 20, 2026, 1:17 p.m.