Triple
T4103854
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SEPTA Route 13 |
E88401
|
entity |
| Predicate | runsPartly |
P53394
|
FINISHED |
| Object | in subway tunnel |
—
|
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: in subway tunnel | Statement: [SEPTA Route 13, runsPartly, in subway tunnel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: runsPartly Context triple: [SEPTA Route 13, runsPartly, in subway tunnel]
-
A.
runsFrom
Indicates that one entity flees or escapes away from another entity.
-
B.
runs
Indicates that an entity moves swiftly on foot, typically using its legs in a continuous, rapid motion.
-
C.
runBy
Indicates that an entity is operated, managed, or controlled by another entity.
-
D.
partiallyCompleted
Indicates that an action, process, or task has been started and progressed to some extent, but has not yet been fully completed.
-
E.
runsApproximately
Indicates that an entity performs a running action in a manner that is close to, but not exactly matching, a specified time, distance, speed, or other running-related measure.
- 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_69aed9484fb881909146f4c772ad277c |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefd31bad88190b850d1dcba14de60 |
completed | March 9, 2026, 5:02 p.m. |
| PD | Predicate disambiguation | batch_69aef90b2ef08190ae84febfd69dd48b |
completed | March 9, 2026, 4:44 p.m. |
| PDg | Predicate description generation | batch_69aefa5c52648190b001027f4dba75cb |
completed | March 9, 2026, 4:50 p.m. |
Created at: March 9, 2026, 3:40 p.m.