Triple
T18798112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Royal British Legion |
E459689
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object | RBL |
—
|
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: RBL | Statement: [Royal British Legion, abbreviation, RBL]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: RBL Context triple: [Royal British Legion, abbreviation, RBL]
-
A.
RBL
chosen
RBL is the commonly used abbreviation for the Royal British Legion, a UK charity that supports members and veterans of the British Armed Forces and their families.
-
B.
RBLR
RBLR is the abbreviated title of the Rutgers Business Law Review, an academic journal focused on issues in business and corporate law.
-
C.
BLB
BLB is the IATA airport code for Panama Pacifico International Airport, a commercial airport serving the Panama City area in Panama.
-
D.
REBLS
REBLS is a specialized academic workshop focused on research advances in programming languages and software systems, typically held as part of the SPLASH conference.
-
E.
RB
RB is a common train service designation in German-speaking countries referring to RegionalBahn, which operates short- to medium-distance regional passenger rail services with frequent stops.
- 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_69d8d398c7d4819091cb2f7e48948aeb |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5a0215084819086bce60f95d08409 |
completed | April 20, 2026, 3:40 a.m. |
Created at: April 10, 2026, 11:53 a.m.