Triple
T225756
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ETH Zurich |
E4310
|
entity |
| Predicate | hasNobelLaureatesAssociated |
P324
|
FINISHED |
| Object | multiple Nobel Prize winners |
—
|
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: multiple Nobel Prize winners | Statement: [ETH Zurich, hasNobelLaureatesAssociated, multiple Nobel Prize winners]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNobelLaureatesAssociated Context triple: [ETH Zurich, hasNobelLaureatesAssociated, multiple Nobel Prize winners]
-
A.
hasNobelLaureatesAffiliated
chosen
Indicates that one entity has Nobel Prize laureates formally associated or connected with it (e.g., as members, staff, or alumni).
-
B.
hasLaureate
Indicates that an entity (such as an award or prize) has a specific person or group as its laureate or recipient.
-
C.
sharedNobelPrizeWith
Indicates that two individuals were jointly awarded the same Nobel Prize, sharing the honor for a particular year and category.
-
D.
NobelPrizeYear
Indicates the specific year in which an entity received or was awarded a Nobel Prize.
-
E.
typicalNumberOfLaureatesPerYear
Indicates the usual or average number of laureates associated with a given award or context in a single year.
- 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_69a257363ffc81909757bde7ab3404da |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25dec53ac8190912f3d79576131fa |
completed | Feb. 28, 2026, 3:15 a.m. |
| PD | Predicate disambiguation | batch_69a25b5739dc8190bad8bfa330ce0499 |
completed | Feb. 28, 2026, 3:04 a.m. |
Created at: Feb. 28, 2026, 2:53 a.m.