Triple
T16667085
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atlantic Avenue Elevated |
E405007
|
entity |
| Predicate | servedTransportMode |
P86086
|
FINISHED |
| Object | passenger rail |
—
|
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: passenger rail | Statement: [Atlantic Avenue Elevated, servedTransportMode, passenger rail]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servedTransportMode Context triple: [Atlantic Avenue Elevated, servedTransportMode, passenger rail]
-
A.
usedTransportationMode
Indicates that an entity traveled or moved using a specified mode of transportation.
-
B.
transportModePresent
chosen
Indicates that a particular mode of transportation is involved or available in the described context or event.
-
C.
successorTransportMode
Indicates that one mode of transport directly follows another in a sequence or chain of transportation.
-
D.
transportModeTo
Indicates the means or mode of transportation used to travel to a specified destination.
-
E.
transportModeImportant
Indicates that the mode of transport used is considered significant or plays an important role in the context of the relationship or action.
- F. None of above.
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_69d8838b5fbc81908c6575c132b82e80 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37c9d9fc48190a8156c029668b544 |
completed | April 18, 2026, 12:44 p.m. |
| PD | Predicate disambiguation | batch_69e319b1d7f08190b5ecb4a68c636c15 |
completed | April 18, 2026, 5:42 a.m. |
Created at: April 10, 2026, 5:18 a.m.