Triple
T4470533
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hindsight Experience Replay |
E98482
|
entity |
| Predicate | publishedAtConference |
P21395
|
FINISHED |
| Object | NeurIPS 2017 |
E96742
|
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: NeurIPS 2017 | Statement: [Hindsight Experience Replay, publishedAtConference, NeurIPS 2017]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: NeurIPS 2017 Context triple: [Hindsight Experience Replay, publishedAtConference, NeurIPS 2017]
-
A.
NeurIPS
chosen
NeurIPS is a premier international conference focused on advances in machine learning, artificial intelligence, and computational neuroscience.
-
B.
NIPS
NIPS is the acronym for the Northern Ireland Prison Service, the government agency responsible for managing prisons and overseeing the custody and rehabilitation of offenders in Northern Ireland.
-
C.
ICLR
ICLR (International Conference on Learning Representations) is a leading annual machine learning conference focused on deep learning and representation learning research.
-
D.
ICML
ICML (International Conference on Machine Learning) is one of the premier global academic conferences focused on research in machine learning and related fields.
-
E.
NeurIPS Test of Time Award
The NeurIPS Test of Time Award is a prestigious honor given at the NeurIPS conference to recognize influential machine learning and AI research papers that have had lasting impact over many years.
- 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_69b3454b4ae481908967426dd37284d6 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b357e4be748190b31aa83d6a8bee53 |
completed | March 13, 2026, 12:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b6286c75b08190bd683d300f6c97f0 |
completed | March 15, 2026, 3:33 a.m. |
Created at: March 12, 2026, 11:34 p.m.