Triple
T3172194
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amtrak Ethan Allen Express |
E66378
|
entity |
| Predicate | namesakeDescription |
P46758
|
FINISHED |
| Object | Revolutionary War patriot from Vermont |
—
|
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: Revolutionary War patriot from Vermont | Statement: [Amtrak Ethan Allen Express, namesakeDescription, Revolutionary War patriot from Vermont]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: namesakeDescription Context triple: [Amtrak Ethan Allen Express, namesakeDescription, Revolutionary War patriot from Vermont]
-
A.
namesakeFullName
Indicates that one entity’s full name is used as the namesake or source of the name for another entity.
-
B.
namesakeStatus
Indicates that one entity serves as the namesake of another, or that two entities share a relationship based on having the same name.
-
C.
namesakeOccupation
Indicates that one entity’s occupation is the same as, or derived from, the occupation associated with the other entity’s namesake.
-
D.
nameOf
Indicates that one entity is the name or designation of another entity.
-
E.
givenNameFor
Indicates that one entity is the personal first name assigned to or used for another entity.
- 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_69ad8585d7988190af37365331093ccd |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada66da23c81908f063b44b48b1e53 |
completed | March 8, 2026, 4:40 p.m. |
| PD | Predicate disambiguation | batch_69ad9e0076b4819094628f1ad10b8f68 |
completed | March 8, 2026, 4:04 p.m. |
| PDg | Predicate description generation | batch_69ada20880e481908ecac09d49b1f1c3 |
completed | March 8, 2026, 4:21 p.m. |
Created at: March 8, 2026, 3:06 p.m.