Triple
T16307841
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | European Synchrotron Radiation Facility |
E395967
|
entity |
| Predicate | annualUsers |
P22398
|
FINISHED |
| Object | thousands of visiting researchers |
—
|
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: thousands of visiting researchers | Statement: [European Synchrotron Radiation Facility, annualUsers, thousands of visiting researchers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: annualUsers Context triple: [European Synchrotron Radiation Facility, annualUsers, thousands of visiting researchers]
-
A.
userCount
chosen
Indicates the number of users associated with or involved in a given context or entity.
-
B.
circulationUsers
Indicates a relationship where users are involved in or affected by the circulation or lending of items within a system.
-
C.
traditionalUsers
Indicates that the associated users adhere to long-established or customary practices, methods, or preferences in the given context.
-
D.
otherUsers
Indicates a relationship where one or more users are distinguished as being different from a given primary or reference user.
-
E.
visitorFrequency
Indicates how often a visitor comes to or interacts with a particular entity or location.
- 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_69d87f23bb088190a16fbb91a1957ea5 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e288d776808190a7c9918477f07216 |
completed | April 17, 2026, 7:24 p.m. |
| PD | Predicate disambiguation | batch_69e219fa5508819097e9d383348bf174 |
completed | April 17, 2026, 11:31 a.m. |
Created at: April 10, 2026, 5:06 a.m.