Triple
T9436126
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RSMC Toulouse |
E227510
|
entity |
| Predicate | typeOfEmergencySupported |
P77203
|
FINISHED |
| Object | radiological emergencies |
—
|
LITERAL 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: radiological emergencies | Statement: [RSMC Toulouse, typeOfEmergencySupported, radiological emergencies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfEmergencySupported Context triple: [RSMC Toulouse, typeOfEmergencySupported, radiological emergencies]
-
A.
typeOfEmergencyService
Indicates the specific category or kind of emergency service associated with or provided in a given situation.
-
B.
emergencyTypesCovered
chosen
Indicates that certain kinds of emergencies are included within the scope of coverage, protection, or response defined by the relationship.
-
C.
hasEmergencyServices
Indicates that the subject provides or is equipped with emergency response services (such as police, fire, or medical assistance).
-
D.
hasEmergencyCare
Indicates that an entity provides or is equipped with emergency medical care services for another entity or individuals.
-
E.
hasEmergencySystems
Indicates that the subject is equipped with or includes systems designed to detect, respond to, or manage emergency situations.
- F. None of above.
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_69ca8437a7ac81908651de48f2d2141d |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd7ede1e148190b5793863a851c92c |
completed | April 1, 2026, 8:23 p.m. |
| PD | Predicate disambiguation | batch_69cca55548488190b171ae695a3212de |
completed | April 1, 2026, 4:55 a.m. |
Created at: March 30, 2026, 7:50 p.m.