Triple
T10923483
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DASA |
E258003
|
entity |
| Predicate | collaboratedWith |
P435
|
FINISHED |
| Object | CASA |
E37410
|
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: CASA | Statement: [DASA, collaboratedWith, CASA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CASA Context triple: [DASA, collaboratedWith, CASA]
-
A.
CASA
chosen
CASA (Construcciones Aeronáuticas S.A.) was a Spanish aircraft manufacturer that became a key predecessor to Airbus through mergers in the European aerospace industry.
-
B.
CASA
CASA is the Australian government authority responsible for regulating civil aviation safety and enforcing air safety standards.
-
C.
CASA
CASA is a prestigious intensive Arabic language and culture program that provides advanced-level training for students and scholars, primarily through immersive study in the Arab world.
-
D.
CASAM
CASAM is the abbreviated name for the Council of Arab Ministers of Social Affairs, a regional body coordinating social policy and welfare initiatives among Arab states.
-
E.
CASAC
CASAC is a scientific advisory committee that provides independent expert advice to the U.S. Environmental Protection Agency on air quality standards and related health and environmental issues.
- 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_69d6aa864ed88190818280ab6791d065 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7708e3fd881908da10f24a856364c |
completed | April 9, 2026, 9:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e2172894d88190b7b27f78e9fd1521 |
completed | April 17, 2026, 11:19 a.m. |
Created at: April 8, 2026, 9:22 p.m.