Triple
T21365104
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chicago "L" Green Line |
E526887
|
entity |
| Predicate | alsoRunsOn |
P11903
|
FINISHED |
| Object | embankment |
—
|
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: embankment | Statement: [Chicago "L" Green Line, alsoRunsOn, embankment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: alsoRunsOn Context triple: [Chicago "L" Green Line, alsoRunsOn, embankment]
-
A.
alsoRuns
Indicates that the subject, in addition to its primary or previously mentioned activity or role, performs or operates another activity, process, or entity.
-
B.
canRunOn
chosen
Indicates that one entity is capable of operating, executing, or functioning on another entity (such as a platform, system, or environment).
-
C.
runsOnHardware
Indicates that a system, software, or process operates using or is executed on a specified hardware platform.
-
D.
runsUnder
Indicates that one process, task, or component operates within the control, environment, or context provided by another system, platform, or framework.
-
E.
launchesOn
Indicates that one entity initiates or begins another entity (such as a process, event, or object) at a specific time or on a specific date.
- 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_69e0b51d8a308190b09113b3b3f9bc15 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e8b06e1ba081908a96928a65da5fa2 |
completed | April 22, 2026, 11:26 a.m. |
| PD | Predicate disambiguation | batch_69e6162bbfc88190a3e75859941b2638 |
completed | April 20, 2026, 12:03 p.m. |
Created at: April 16, 2026, 5:09 p.m.