Triple
T24905996
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KCS |
E623708
|
entity |
| Predicate | hasReportingMarkFormat |
P168013
|
FINISHED |
| Object | three-letter alphabetic code |
—
|
LITERAL 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: three-letter alphabetic code | Statement: [KCS, hasReportingMarkFormat, three-letter alphabetic code]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasReportingMarkFormat Context triple: [KCS, hasReportingMarkFormat, three-letter alphabetic code]
-
A.
usedReportingMarks
Indicates that an entity employed specific railroad reporting marks to identify rolling stock or operations.
-
B.
hasProductionFormatEligibility
Indicates that something qualifies for or is allowed to use a particular production format.
-
C.
hasColorFormat
Indicates that an entity uses or is associated with a specific color representation or encoding format.
-
D.
hasImprintStyle
Indicates that one entity bears or exhibits a particular style, pattern, or form of imprint associated with another entity.
-
E.
hasProductionFormat
Indicates that an entity is associated with, or presented in, a particular production or media format.
- F. None of above. chosen
Provenance (4 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_69e2fac797cc8190b30d77f4121099ac |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f673633d288190b52ceb9f8a057c44 |
completed | May 2, 2026, 9:57 p.m. |
| PD | Predicate disambiguation | batch_69f66ec3d3d48190ab2f2b71939e572e |
completed | May 2, 2026, 9:38 p.m. |
| PDg | Predicate description generation | batch_69f67256d064819094be04fc1bbbc635 |
completed | May 2, 2026, 9:53 p.m. |
Created at: April 18, 2026, 5:27 a.m.