Triple
T26271314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Farragut Crossing (virtual tunnel) |
E660429
|
entity |
| Predicate | transferWithinSystem |
P177290
|
FINISHED |
| Object | Metrorail |
—
|
NE NERFINISHED |
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: Metrorail | Statement: [Farragut Crossing (virtual tunnel), transferWithinSystem, Metrorail]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transferWithinSystem Context triple: [Farragut Crossing (virtual tunnel), transferWithinSystem, Metrorail]
-
A.
transferBetween
Indicates a movement or handover of something from one entity to another, typically changing its location, ownership, or control between them.
-
B.
transferType
Indicates the specific method or category of how something is transferred from one entity to another.
-
C.
transferFeature
Indicates a relationship where a feature, attribute, or capability is moved or reassigned from one entity to another.
-
D.
transferAfter
Indicates that one entity transfers something to another entity only after a specified event or condition has occurred.
-
E.
transferComplex
Indicates the movement or relocation of a multi-component entity or system from one context, location, or state to another.
- 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_69ee812960d081909cff6085cc9fa3a6 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f6fb93224881908fc66fe76115fcdb |
completed | May 3, 2026, 7:38 a.m. |
| PD | Predicate disambiguation | batch_69f6f969b4cc8190afb473a2d8b110bc |
completed | May 3, 2026, 7:29 a.m. |
| PDg | Predicate description generation | batch_69f6fb17d5ec81909091e37e1ddbe577 |
completed | May 3, 2026, 7:36 a.m. |
Created at: April 26, 2026, 9:50 p.m.