Triple
T132938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Francis Scott Key |
E2689
|
entity |
| Predicate | wroteWorkAtLocation |
P1144
|
FINISHED |
| Object | aboard a ship in Baltimore Harbor |
—
|
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: aboard a ship in Baltimore Harbor | Statement: [Francis Scott Key, wroteWorkAtLocation, aboard a ship in Baltimore Harbor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wroteWorkAtLocation Context triple: [Francis Scott Key, wroteWorkAtLocation, aboard a ship in Baltimore Harbor]
-
A.
writtenAtLocation
chosen
Indicates that an act of writing occurred at a specific physical or geographical location.
-
B.
writtenAtEvent
Indicates that a writing or inscription activity occurred during or in connection with a specific event.
-
C.
writtenDuring
Indicates that the creation or authorship of something took place within a specified time period or historical event.
-
D.
wrote
Indicates that an entity is the author or creator of a written work involving another entity.
-
E.
writtenForm
Indicates that one entity is the textual or orthographic representation (spelling or written version) of another entity.
- 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_69a2520c0f3481908b0ed054a2fca8d0 |
completed | Feb. 28, 2026, 2:25 a.m. |
| NER | Named-entity recognition | batch_69a25855baf48190a1b63f2e5865d957 |
completed | Feb. 28, 2026, 2:52 a.m. |
| PD | Predicate disambiguation | batch_69a2564edb488190974dc00eb9ac37d9 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:30 a.m.