Triple
T17493163
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | M-6 (Michigan highway) |
E425977
|
entity |
| Predicate | hasJunctionWith |
P1018
|
FINISHED |
| Object |
M-121
M-121 is a state trunkline highway in western Michigan that serves as a regional connector between communities southwest of Grand Rapids.
|
E1271568
|
NE FINISHED |
How this triple was built (4 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: M-121 | Statement: [M-6 (Michigan highway), hasJunctionWith, M-121]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: M-121 Context triple: [M-6 (Michigan highway), hasJunctionWith, M-121]
-
A.
M-125
M-125 is a state highway route that serves as a primary roadway connection for the Monroe area.
-
B.
M-102
M-102 is a state trunkline highway in Michigan best known as Detroit’s Eight Mile Road, a major east–west thoroughfare that serves as a cultural and socioeconomic dividing line in the region.
-
C.
M-102
M-102 is a regional road in the Community of Madrid, Spain, that provides access to and from the town of Torrelaguna.
-
D.
M-115
M-115 is a state trunkline highway in Michigan that serves as a regional connector route through the central and northwestern parts of the Lower Peninsula.
-
E.
M-131
M-131 is a regional road in the Community of Madrid, Spain, that provides access to and from the town of Torrelaguna.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: M-121 Triple: [M-6 (Michigan highway), hasJunctionWith, M-121]
Generated description
M-121 is a state trunkline highway in western Michigan that serves as a regional connector between communities southwest of Grand Rapids.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: M-121 Target entity description: M-121 is a state trunkline highway in western Michigan that serves as a regional connector between communities southwest of Grand Rapids.
-
A.
M-125
M-125 is a state highway route that serves as a primary roadway connection for the Monroe area.
-
B.
M-102
M-102 is a regional road in the Community of Madrid, Spain, that provides access to and from the town of Torrelaguna.
-
C.
M-102
M-102 is a state trunkline highway in Michigan best known as Detroit’s Eight Mile Road, a major east–west thoroughfare that serves as a cultural and socioeconomic dividing line in the region.
-
D.
M-115
M-115 is a state trunkline highway in Michigan that serves as a regional connector route through the central and northwestern parts of the Lower Peninsula.
-
E.
M-131
M-131 is a regional road in the Community of Madrid, Spain, that provides access to and from the town of Torrelaguna.
- F. None of above. chosen
Provenance (5 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_69d889dccf7481909264a1844a2e9100 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e451d6bd548190b4c6fae27c2a9ae8 |
completed | April 19, 2026, 3:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01c202b7c48190bb2d58a77c8eca80 |
completed | May 11, 2026, 11:48 a.m. |
| NEDg | Description generation | batch_6a01c2aa19408190840547b60786cc18 |
completed | May 11, 2026, 11:51 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a01c35d05388190ade7044202781e20 |
completed | May 11, 2026, 11:54 a.m. |
Created at: April 10, 2026, 5:48 a.m.