Triple
T15719843
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coll airfield |
E381060
|
entity |
| Predicate | hasICAOcode |
P419
|
FINISHED |
| Object | EGEL |
E511040
|
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: EGEL | Statement: [Coll airfield, hasICAOcode, EGEL]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: EGEL Context triple: [Coll airfield, hasICAOcode, EGEL]
-
A.
EGEL
chosen
EGEL is the ICAO airport code for Coll Airport, a small airfield serving the island of Coll in Scotland.
-
B.
EGE
EGE is the IATA airport code for Eagle County Regional Airport, a commercial airport serving the Vail and Eagle Valley region in Colorado, USA.
-
C.
Eggel
Eggel is a small river in Germany that serves as a tributary of the Diemel.
-
D.
Aeg
Aeg was a German electricity company that played a key role in early 20th-century industrial design and technology, notably supporting avant-garde projects like the Light-Space Modulator.
-
E.
EGGZ
EGGZ is the UN/LOCODE designation for the Giza Governorate region in Egypt, used in international trade and transport logistics.
- 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_69d86d9bf930819082b30cf6d169297c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f932a248190b65ecfb2bc56e715 |
completed | April 16, 2026, 2:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff75852cf88190be054160d5cbc675 |
completed | May 9, 2026, 5:57 p.m. |
Created at: April 10, 2026, 4:45 a.m.