Triple
T3165827
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Potomac Yard–VT Metrorail station |
E66208
|
entity |
| Predicate | hasNameSuffix |
P46465
|
FINISHED |
| Object | VT |
—
|
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: VT | Statement: [Potomac Yard–VT Metrorail station, hasNameSuffix, VT]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNameSuffix Context triple: [Potomac Yard–VT Metrorail station, hasNameSuffix, VT]
-
A.
hasSuffixedRoute
Indicates that a route is a variant or extension of another base route, distinguished by an added suffix in its identifier.
-
B.
hasComponentSurname
Indicates that an entity’s full name includes a specified surname as one of its component parts.
-
C.
hasBaseSurname
Indicates that an entity’s surname is derived from, or fundamentally corresponds to, a specified base or canonical surname.
-
D.
patronymicSuffix
Indicates that one entity is a suffix added to a personal name to denote lineage or descent from another person, typically the father.
-
E.
hasSymbolNamedAfter
Indicates that one entity has a symbol whose name is derived from or dedicated to 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_69ada6424ee48190a29891ffbbc3811d |
completed | March 8, 2026, 4:39 p.m. |
| PD | Predicate disambiguation | batch_69ad9dfe0a948190928f2201d671c654 |
completed | March 8, 2026, 4:04 p.m. |
| PDg | Predicate description generation | batch_69ada148e9108190b363dd0f1a94ac8e |
completed | March 8, 2026, 4:18 p.m. |
Created at: March 8, 2026, 3:06 p.m.