Triple
T18228209
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marquette Iron Range |
E436473
|
entity |
| Predicate | startOfCommercialShipping |
P1929
|
FINISHED |
| Object | 1850s |
—
|
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: 1850s | Statement: [Marquette Iron Range, startOfCommercialShipping, 1850s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startOfCommercialShipping Context triple: [Marquette Iron Range, startOfCommercialShipping, 1850s]
-
A.
beganCommercialProduction
Indicates that an entity started producing something commercially, marking the commencement of its large-scale or market-oriented production.
-
B.
firstCommercialFlightDate
Indicates the calendar date on which an entity’s first commercial flight or revenue-earning air service took place.
-
C.
firstCommercialLaunchDate
Indicates the calendar date on which an entity’s product, service, or operation was first made commercially available to the public.
-
D.
locationOfFirstCommercialUse
Indicates the place where something was first used commercially.
-
E.
firstCommercialUse
chosen
Indicates the earliest point in time at which something was used commercially or put into commercial operation.
- 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_69d8b9103a8081908bbb0836fef10efd |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4f4b0ed5c819096f4fd3a8debc1a4 |
completed | April 19, 2026, 3:28 p.m. |
| PD | Predicate disambiguation | batch_69e4332336cc8190808b9c70c888ba65 |
completed | April 19, 2026, 1:42 a.m. |
Created at: April 10, 2026, 10:33 a.m.