Triple
T5073764
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fort Gratiot Lighthouse |
E114341
|
entity |
| Predicate | isOldestLighthouseOn |
P61255
|
FINISHED |
| Object | Great Lakes still in operation |
—
|
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: Great Lakes still in operation | Statement: [Fort Gratiot Lighthouse, isOldestLighthouseOn, Great Lakes still in operation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isOldestLighthouseOn Context triple: [Fort Gratiot Lighthouse, isOldestLighthouseOn, Great Lakes still in operation]
-
A.
isOldestMuseumIn
Indicates that a museum is the most ancient or earliest established museum within a specified location or region.
-
B.
oneOfTheOldestOn
Indicates that one entity is among the earliest or longest-existing examples within the set defined by another entity.
-
C.
isOldestCityIn
Indicates that one city holds the distinction of being the most ancient or earliest established within a specified region, country, or group of cities.
-
D.
oldestTownIn
Indicates that a town is the most ancient or earliest established town within a specified larger area or region.
-
E.
isOneOfOldestStationsInSystem
Indicates that the station is among the earliest or first-built stations within the entire system.
- 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_69bd443cf28c8190ad371d603563dbdd |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd74d0be1c819081b26235fe602a30 |
completed | March 20, 2026, 4:24 p.m. |
| PD | Predicate disambiguation | batch_69bd7157fe608190b4515d56fdd0a616 |
completed | March 20, 2026, 4:10 p.m. |
| PDg | Predicate description generation | batch_69bd73d90b608190bd6c2407e84e2b64 |
completed | March 20, 2026, 4:20 p.m. |
Created at: March 20, 2026, 1:39 p.m.