Triple
T33906224
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | suburban Detroit, Michigan |
E869188
|
entity |
| Predicate | hasCommuterRelationshipWith |
P114783
|
FINISHED |
| Object | Detroit, Michigan |
E2603
|
NE 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: Detroit, Michigan | Statement: [suburban Detroit, Michigan, hasCommuterRelationshipWith, Detroit, Michigan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCommuterRelationshipWith Context triple: [suburban Detroit, Michigan, hasCommuterRelationshipWith, Detroit, Michigan]
-
A.
hasCommuterLinks
chosen
Indicates that there are established transportation connections enabling regular travel between two locations.
-
B.
commutesBetween
Indicates a regular pattern of travel back and forth between two locations, typically for work, study, or routine activities.
-
C.
transportRelationship
Indicates a relationship where one entity moves, carries, or conveys another entity from one location to another.
-
D.
hasTransportationRelation
Indicates a relationship in which one entity provides, uses, is connected by, or is otherwise associated with a means or mode of transportation to another entity or location.
-
E.
anticommutesWith
Indicates that applying the two operations in opposite orders yields results that differ by a sign (their composition changes sign when the order is reversed).
- F. None of above.
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_69f34997703c8190866b1d404bce531f |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a037e0953908190b2930b3c06a40129 |
completed | May 12, 2026, 7:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a36a01a2be88190b6fcd221016af43b |
completed | June 20, 2026, 2:13 p.m. |
| PD | Predicate disambiguation | batch_6a0379f6c3308190b954f7810214ceed |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:48 a.m.