Triple
T10765351
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 23rd Special Air Service Regiment (Reserve) |
E253938
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object | 23 SAS(R) |
E51750
|
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: 23 SAS(R) | Statement: [23rd Special Air Service Regiment (Reserve), abbreviation, 23 SAS(R)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 23 SAS(R) Context triple: [23rd Special Air Service Regiment (Reserve), abbreviation, 23 SAS(R)]
-
A.
23 SAS
chosen
23 SAS is a British Army Reserve regiment of the Special Air Service, specializing in long-range reconnaissance and special operations in support of UK special forces.
-
B.
21 SAS
21 SAS is a reserve regiment of the British Army’s Special Air Service, specializing in high-level special operations and support to regular SAS units.
-
C.
SAS-B
SAS-B is a U.S. Navy satellite from the 1970s that was part of the Space Surveillance (SAS) series used to study celestial X-ray sources.
-
D.
S-23
S-23 is an International Hydrographic Organization publication that standardizes the naming and limits of the world’s oceans and seas.
-
E.
SAS-4
SAS-4 is the fourth-generation Serial Attached SCSI (SAS) interface standard that significantly increases data transfer speeds and bandwidth for enterprise storage systems.
- 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_69d6aa5f54f4819082d0bbcb6f8797e6 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d731a5d5248190badfc5a8ab0215d6 |
completed | April 9, 2026, 4:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de235fe7748190ba004f889da389ff |
completed | April 14, 2026, 11:22 a.m. |
Created at: April 8, 2026, 9:16 p.m.