Triple
T10790723
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adams County, Colorado |
E254570
|
entity |
| Predicate | postalAbbreviation |
P43
|
FINISHED |
| Object | CO |
E223873
|
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: CO | Statement: [Adams County, Colorado, postalAbbreviation, CO]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CO Context triple: [Adams County, Colorado, postalAbbreviation, CO]
-
A.
CO
CO is the Italian vehicle registration code for the Province of Como in the Lombardy region.
-
B.
CO
CO is a postcode area in the United Kingdom covering Colchester and surrounding parts of Essex, including towns such as Clacton-on-Sea.
-
C.
CO
chosen
CO is the official two-letter United States Postal Service abbreviation for the state of Colorado.
-
D.
CO
CO is the former IATA airline designator for Continental Airlines, a major U.S. carrier that merged with United Airlines.
-
E.
CO
CO is the two-letter ISO 3166-1 alpha-2 country code assigned to Colombia for international identification and standardization purposes.
- 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_69d6aa609f008190a294200aefcb7bd5 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d732f5b8248190a633dc44ae620a3a |
completed | April 9, 2026, 5:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de5637ec50819087f1a0372f89197d |
completed | April 14, 2026, 2:59 p.m. |
Created at: April 8, 2026, 9:17 p.m.