Triple
T9933786
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | École Royale Militaire |
E192707
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object | ERM |
E37222
|
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: ERM | Statement: [École Royale Militaire, shortName, ERM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ERM Context triple: [École Royale Militaire, shortName, ERM]
-
A.
ERM
chosen
ERM is the French-language abbreviation for Belgium’s Royal Military Academy, the country’s principal institution for training future officers of the armed forces.
-
B.
ERM
ERM is a European Union system designed to reduce exchange rate variability and achieve monetary stability in preparation for economic and monetary union.
-
C.
ER
ER is the vehicle registration code assigned to the German city of Erlangen in the state of Bavaria.
-
D.
ER
ER is the zone code for Eastern Railway, one of the major railway zones of Indian Railways headquartered in Kolkata.
-
E.
ER
ER is a critically acclaimed American medical drama television series that follows the personal and professional lives of staff in a busy Chicago emergency room.
- 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_69ca82dd978c8190947124ab0d3315ac |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb5b89c808190a2e766025dd53bd5 |
completed | April 2, 2026, 12:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d228ddecfc8190850a098bf4074cc3 |
completed | April 5, 2026, 9:18 a.m. |
Created at: March 30, 2026, 8:44 p.m.