Triple
T31045073
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amtrak Michigan Line |
E791100
|
entity |
| Predicate | hasOwnerSegment |
P171125
|
FINISHED |
| Object | State of Michigan |
—
|
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: State of Michigan | Statement: [Amtrak Michigan Line, hasOwnerSegment, State of Michigan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOwnerSegment Context triple: [Amtrak Michigan Line, hasOwnerSegment, State of Michigan]
-
A.
hasSegmentOn
Indicates that one entity includes or occupies a specific segment or portion on another entity (such as a line, path, or sequence).
-
B.
hasSegmentFrom
Indicates that something includes or contains a segment that originates from or is derived from another specified source.
-
C.
hasOwnerStructure
Indicates that an entity is associated with, or governed by, a particular ownership structure or ownership arrangement.
-
D.
hasSegmentWith
Indicates that an entity contains or includes at least one segment that satisfies a specified condition or matches a given segment.
-
E.
hasDeFactoSegmentWith
Indicates that one entity includes or is associated with a segment that functions in practice (de facto) as part of it, even if not formally or legally defined as such.
- 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_69f224ca2fa881908a3ac5fedf207b90 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f698ad83a08190a6834056ccc3e3a4 |
completed | May 3, 2026, 12:37 a.m. |
| PD | Predicate disambiguation | batch_69f69664142c8190bc695501056b0236 |
completed | May 3, 2026, 12:27 a.m. |
| PDg | Predicate description generation | batch_69f697e92e2c8190bed50d5ba0981b64 |
completed | May 3, 2026, 12:33 a.m. |
Created at: April 29, 2026, 8:59 p.m.