Triple
T20074086
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terminal C (former) |
E499812
|
entity |
| Predicate | hasIATAAirport |
P17503
|
FINISHED |
| Object | MCI |
—
|
NE NERFINISHED |
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: MCI | Statement: [Terminal C (former), hasIATAAirport, MCI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MCI Context triple: [Terminal C (former), hasIATAAirport, MCI]
-
A.
MCI
chosen
MCI is a major commercial airport serving the Kansas City metropolitan area in Missouri, United States.
-
B.
MCI
MCI was the former statutory body responsible for establishing and maintaining high standards of medical education and registration of medical practitioners in India.
-
C.
MCI-Shirley
MCI-Shirley is a medium- and minimum-security state prison for men located in Shirley, Massachusetts.
-
D.
MCI Inc.
MCI Inc. was a major American telecommunications company and long-distance service provider that played a key role in breaking AT&T’s monopoly before eventually being acquired by Verizon.
-
E.
MCA
MCA is the UK government executive agency responsible for maritime safety, search and rescue coordination, and preventing pollution from ships in UK waters.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da627770948190997f486f9a2e370f |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66439efe881909a068c3f05022421 |
completed | April 20, 2026, 5:36 p.m. |
Created at: April 11, 2026, 3:40 p.m.