Triple
T28828285
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Homestake experiment |
E727970
|
entity |
| Predicate | nobelPrizeConnection |
P9522
|
FINISHED |
| Object | contributed to 2002 Nobel Prize in Physics |
—
|
LITERAL 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: contributed to 2002 Nobel Prize in Physics | Statement: [Homestake experiment, nobelPrizeConnection, contributed to 2002 Nobel Prize in Physics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nobelPrizeConnection Context triple: [Homestake experiment, nobelPrizeConnection, contributed to 2002 Nobel Prize in Physics]
-
A.
nobelPrizeRelated
chosen
Indicates that there is a connection or association between an entity and the Nobel Prize, such as receiving, being nominated for, or otherwise being significantly linked to it.
-
B.
NobelPrizeShare
Indicates the proportion or fraction of a Nobel Prize that is allocated to a particular laureate or laureate entity.
-
C.
NobelPrizeCoLaureate
Indicates that two or more individuals share the same Nobel Prize as co-recipients for a particular award and year.
-
D.
authorNobelLaureate
Indicates that the author is a recipient of a Nobel Prize.
-
E.
numberOfNobelPrizes
Indicates the count of Nobel Prizes that have been awarded to a given entity.
- F. None of above.
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_69f0319dc6088190bbfaa206d40ed74a |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f65939b9c481909b9ca8035227862b |
completed | May 2, 2026, 8:06 p.m. |
| PD | Predicate disambiguation | batch_69f65762b5e481908a30ca963dcba4be |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 28, 2026, 6:36 a.m.