Triple
T16022604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pilot Island Light |
E388638
|
entity |
| Predicate | locatedInBayOrGulf |
P109263
|
FINISHED |
| Object | near the entrance to Green Bay |
—
|
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: near the entrance to Green Bay | Statement: [Pilot Island Light, locatedInBayOrGulf, near the entrance to Green Bay]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedInBayOrGulf Context triple: [Pilot Island Light, locatedInBayOrGulf, near the entrance to Green Bay]
-
A.
locatedInBayOf
chosen
Indicates that something is situated within or directly on a specific bay.
-
B.
bayOf
Indicates that one location is a bay that forms an inlet or coastal indentation associated with another geographic entity, such as a sea, ocean, or coastline.
-
C.
locatedInSeaBasin
Indicates that something is situated within or belongs to a particular sea basin.
-
D.
hasGulf
Indicates that one geographic entity contains or is bordered by a gulf associated with another entity.
-
E.
locatedInBasin
Indicates that one geographical or hydrological feature lies within the drainage or catchment area of a specified basin.
- 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_69d86dabcb7c8190b6a39d6831d2fa1b |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1858a00888190b8505071575dc56f |
completed | April 17, 2026, 12:57 a.m. |
| PD | Predicate disambiguation | batch_69e1826a4f7c8190aba6d4f1075141b0 |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 4:55 a.m.