Triple
T9135086
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Air Canada |
E219179
|
entity |
| Predicate | hasIcaoCode |
P419
|
FINISHED |
| Object | ACA |
E219179
|
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: ACA | Statement: [Air Canada, hasIcaoCode, ACA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ACA Context triple: [Air Canada, hasIcaoCode, ACA]
-
A.
ACA
ACA is a professional scientific organization that promotes the study and application of crystallography and structural science, primarily in North America.
-
B.
ACA
ACA is the common abbreviation for the Affordable Care Act, a major U.S. health care reform law enacted in 2010 to expand insurance coverage and consumer protections.
-
C.
ACA
chosen
ACA is the three-letter ICAO airline designator used to identify Air Canada in international aviation operations and communications.
-
D.
ACA
ACA is the acronym commonly used for the Army Comrades Association, an Irish nationalist organization active in the early 20th century.
-
E.
ACA
ACA is a subset of the Atacama Large Millimeter/submillimeter Array (ALMA) consisting of closely spaced radio telescopes designed to improve imaging of extended astronomical objects.
- 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_69ca83e012288190a5771058adbaabd2 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca8de0dec8190978c80b9ec8bf25c |
completed | April 1, 2026, 5:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d047efc5e48190bc8c4a7e865faef9 |
completed | April 3, 2026, 11:06 p.m. |
Created at: March 30, 2026, 7:18 p.m.