Triple
T21818724
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LISA Consortium |
E538667
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object | LISA |
—
|
NE NERFINISHED |
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: LISA | Statement: [LISA Consortium, abbreviation, LISA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LISA Context triple: [LISA Consortium, abbreviation, LISA]
-
A.
LISA line
The LISA line is a route of the CDGVAL automated people mover system serving Paris Charles de Gaulle Airport.
-
B.
LISA lab
LISA lab is a machine learning research group at the Université de Montréal known for pioneering deep learning methods and tools.
-
C.
LISA Consortium
chosen
The LISA Consortium is an international collaboration of scientists and institutions dedicated to developing and operating the Laser Interferometer Space Antenna (LISA), a space-based gravitational wave observatory led by ESA with NASA participation.
-
D.
Lis
Lis is a diminutive form of the given name Lisa, commonly used as a short or affectionate variant.
-
E.
Lis
Lis is a small unincorporated rural community located in Jasper County in the U.S. state of Illinois.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c475038c8190abb9b1a20eb8ff50 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f07ccd0d908190a43af4fcc7d6ca03 |
completed | April 28, 2026, 9:24 a.m. |
Created at: April 16, 2026, 6:54 p.m.