Triple
T4657731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Drum Point Lighthouse |
E102448
|
entity |
| Predicate | servedShipping |
P50377
|
FINISHED |
| Object | Patuxent River traffic |
—
|
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: Patuxent River traffic | Statement: [Drum Point Lighthouse, servedShipping, Patuxent River traffic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servedShipping Context triple: [Drum Point Lighthouse, servedShipping, Patuxent River traffic]
-
A.
servedShip
Indicates that one entity performed service or duty aboard, or in direct support of, a particular ship.
-
B.
servedWith
Indicates that one item is customarily presented, provided, or consumed together with another as an accompaniment or side.
-
C.
served
Indicates that one entity provided a service, assistance, or role-based function to or for another entity.
-
D.
servedDestination
chosen
Indicates that a service or action is directed toward, or provided to, a particular destination.
-
E.
shippingFunction
Indicates the method or process by which goods are transported or delivered from a sender to a recipient.
- 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_69bd43d823288190952279faa0d1d066 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd631a855c81909773737fd238a14d |
completed | March 20, 2026, 3:09 p.m. |
| PD | Predicate disambiguation | batch_69bd62126b0c81909ba3f21b21e30d54 |
completed | March 20, 2026, 3:04 p.m. |
Created at: March 20, 2026, 1:15 p.m.