Triple
T26202639
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HMS Madagascar |
E655269
|
entity |
| Predicate | notableCrewMemberRankLater |
P42936
|
FINISHED |
| Object | Admiral Sir Provo Wallis |
—
|
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: Admiral Sir Provo Wallis | Statement: [HMS Madagascar, notableCrewMemberRankLater, Admiral Sir Provo Wallis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableCrewMemberRankLater Context triple: [HMS Madagascar, notableCrewMemberRankLater, Admiral Sir Provo Wallis]
-
A.
notableRank
Indicates that an entity holds a distinguished or significant position or level within a ranking or hierarchy.
-
B.
hasNotableCrewMember
chosen
Indicates that an entity is associated with a crew member who is considered notable or distinguished in some way.
-
C.
notableOfficerRole
Indicates that an entity holds or has held a particularly significant or distinguished officer position within an organization or institution.
-
D.
hasCrewRole
Indicates that an entity serves in a specific role or position within a crew associated with another entity.
-
E.
hasCrewMember
Indicates that an entity includes or employs another entity as a member of its crew.
- 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_69ee5b48236c81908fe385b6afc4f60b |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69fe6e492bf8819080b25221d13445ea |
completed | May 8, 2026, 11:14 p.m. |
| PD | Predicate disambiguation | batch_69fe6dd33a6881908fe9bbbc184cab51 |
completed | May 8, 2026, 11:12 p.m. |
Created at: April 26, 2026, 8:49 p.m.