Triple
T35540665
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lusitania-class ocean liners |
E1027049
|
entity |
| Predicate | mailContractFrom |
P183226
|
FINISHED |
| Object | British government |
—
|
NE NERFINISHED |
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: British government | Statement: [Lusitania-class ocean liners, mailContractFrom, British government]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mailContractFrom Context triple: [Lusitania-class ocean liners, mailContractFrom, British government]
-
A.
mailContractWith
Indicates that one party sends or delivers a contract to another party via mail as part of a transactional or formal process.
-
B.
mailRoute
Indicates a route or path along which mail or postal items are transported between locations.
-
C.
mailCollectedFrom
Indicates that mail has been picked up or retrieved from a specified source or location.
-
D.
mailedTo
Indicates that something was sent or delivered by mail from one entity to another as the recipient.
-
E.
addressFormFor
Indicates the form of address or mode of speaking that one entity should use when referring to or speaking to another entity.
- 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_69f76e008ba08190927acd8e5e0344c8 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f79a54aa3c8190b2bb5d790b2d42d4 |
completed | May 3, 2026, 6:56 p.m. |
| PD | Predicate disambiguation | batch_69f7961970408190b669cc556e30a608 |
completed | May 3, 2026, 6:38 p.m. |
| PDg | Predicate description generation | batch_69f79a53ccc481908421ae16e69aa8a4 |
completed | May 3, 2026, 6:56 p.m. |
Created at: May 3, 2026, 4:04 p.m.