Triple
T18198773
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MegaCam |
E435727
|
entity |
| Predicate | sciencePrograms |
P2573
|
FINISHED |
| Object | weak gravitational lensing surveys |
—
|
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: weak gravitational lensing surveys | Statement: [MegaCam, sciencePrograms, weak gravitational lensing surveys]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sciencePrograms Context triple: [MegaCam, sciencePrograms, weak gravitational lensing surveys]
-
A.
researchProgram
chosen
Indicates that an entity is engaged in, associated with, or part of a structured research initiative or program.
-
B.
sponsoredPrograms
Indicates that an entity provides financial or resource support to specific programs or initiatives.
-
C.
inspiredPrograms
Indicates that one entity served as a source of inspiration or influence for the creation or design of another entity’s programs.
-
D.
stateProgram
Indicates that a program is organized, funded, or administered by a governmental state authority.
-
E.
recommendedProgram
Indicates that one entity suggests or endorses another entity as a suitable or preferred program for a particular purpose or user.
- 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_69d8b90dba6481908e119eb9aa4ca0cb |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4e0d545f4819090285d1446bd3c27 |
completed | April 19, 2026, 2:04 p.m. |
| PD | Predicate disambiguation | batch_69e4331e92408190ad607ba4956a3897 |
completed | April 19, 2026, 1:42 a.m. |
Created at: April 10, 2026, 10:31 a.m.