Triple
T35780553
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chief of the Maritime Staff |
E1034425
|
entity |
| Predicate | isFormerTitleOf |
P155834
|
FINISHED |
| Object | Commander of the Royal Canadian Navy |
—
|
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: Commander of the Royal Canadian Navy | Statement: [Chief of the Maritime Staff, isFormerTitleOf, Commander of the Royal Canadian Navy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isFormerTitleOf Context triple: [Chief of the Maritime Staff, isFormerTitleOf, Commander of the Royal Canadian Navy]
-
A.
hasFormerTitle
chosen
Indicates that an entity previously held a specific title or position but no longer does.
-
B.
hasMasterTitleFormer
Indicates that an entity previously held, but no longer holds, a particular master title.
-
C.
previousHeadOfStateTitle
Indicates that one entity is the official title or designation held by another entity in its role as a former head of state.
-
D.
predecessorTitleHolder
Indicates that one entity previously held a particular title or position before another entity.
-
E.
isSeniorTitle
Indicates that one title holds a higher or more senior rank or status relative to another title.
- 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_69f76e14a1e081908eddd57bd6fdb3be |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7aa699d68819081ed363931894ab3 |
completed | May 3, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69f7a8d219f8819081dc4ce3c83ca0cb |
completed | May 3, 2026, 7:58 p.m. |
Created at: May 3, 2026, 4:06 p.m.