Triple
T10903576
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | sinking of the RMS Lusitania |
E257507
|
entity |
| Predicate | warningPublication |
P96325
|
FINISHED |
| Object | newspaper advertisements in the United States |
—
|
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: newspaper advertisements in the United States | Statement: [sinking of the RMS Lusitania, warningPublication, newspaper advertisements in the United States]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: warningPublication Context triple: [sinking of the RMS Lusitania, warningPublication, newspaper advertisements in the United States]
-
A.
warningType
Indicates the specific category or classification of a warning associated with an entity or event.
-
B.
warningIssued
Indicates that a formal warning or alert has been communicated from one entity to another regarding a potential or existing risk, problem, or violation.
-
C.
warningSubject
Indicates that one entity is the topic or focus of a warning issued by another entity.
-
D.
warningGivenBy
Indicates that one entity issues or delivers a warning to another entity.
-
E.
warningCall
Indicates that one entity initiates a call to another specifically to warn them about a danger, risk, or important cautionary information.
- 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_69d6aa8550c8819095508a2ed9acf3db |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d761a5dffc8190927b0928978646a4 |
completed | April 9, 2026, 8:21 a.m. |
| PD | Predicate disambiguation | batch_69d70d3d69e08190bb369e9a7927142c |
completed | April 9, 2026, 2:21 a.m. |
| PDg | Predicate description generation | batch_69d7101de31c819090707635f6790559 |
completed | April 9, 2026, 2:34 a.m. |
Created at: April 8, 2026, 9:22 p.m.