Triple
T22690198
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | L01BA04 |
E561030
|
entity |
| Predicate | ATCLevel2 |
P23165
|
FINISHED |
| Object | L01 |
—
|
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: L01 | Statement: [L01BA04, ATCLevel2, L01]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ATCLevel2 Context triple: [L01BA04, ATCLevel2, L01]
-
A.
providesATCServiceTo
Indicates that one entity delivers air traffic control services or support to another entity.
-
B.
appliesToAirspaceOf
Indicates that a rule, restriction, or condition is specifically relevant to, or in effect within, a particular airspace.
-
C.
hasATCCode
Indicates that a pharmaceutical product or substance is assigned a specific Anatomical Therapeutic Chemical (ATC) classification code.
-
D.
ICAOClassificationSystem
Indicates a relationship where an entity is categorized or defined according to the standards and categories of the ICAO (International Civil Aviation Organization) classification system.
-
E.
hasATCClass
chosen
Indicates that a drug or medicinal product is assigned to a specific Anatomical Therapeutic Chemical (ATC) classification category.
- 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_69e2454d71b48190a1f80af9f82b6fcf |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1789a1fd08190bce5fa0babe695d3 |
completed | April 29, 2026, 3:18 a.m. |
| PD | Predicate disambiguation | batch_69ee62b2259c819091ed1387a748b9f3 |
completed | April 26, 2026, 7:08 p.m. |
Created at: April 17, 2026, 3:13 p.m.