Triple
T9885811
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | VISTA telescope |
E180928
|
entity |
| Predicate | instrument |
P792
|
FINISHED |
| Object | VIRCAM |
E666537
|
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: VIRCAM | Statement: [VISTA telescope, instrument, VIRCAM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: VIRCAM Context triple: [VISTA telescope, instrument, VIRCAM]
-
A.
VIRCAM
chosen
VIRCAM is the wide-field infrared camera used on the VISTA telescope to conduct large-scale near-infrared sky surveys.
-
B.
MegaCam
MegaCam is a wide-field optical imaging camera used for deep-sky astronomical surveys on the Canada–France–Hawaii Telescope.
-
C.
WIRCam
WIRCam is a wide-field infrared camera used for astronomical imaging on the Canada–France–Hawaii Telescope.
-
D.
VISTA telescope
The VISTA telescope is a 4.1-meter wide-field survey telescope in Chile designed primarily for large-scale near-infrared sky surveys.
-
E.
LSST Camera
The LSST Camera is a massive, wide-field digital camera designed to capture deep, high-resolution images of the night sky for the Vera C. Rubin Observatory’s decade-long sky survey.
- 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_69ca828082cc8190a40f8d299caa6545 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cdb45659748190a3ebd1abe23c8779 |
completed | April 2, 2026, 12:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1eafc76b0819098e481bb17a3af2b |
completed | April 5, 2026, 4:54 a.m. |
Created at: March 30, 2026, 8:38 p.m.