Triple
T6246980
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jack Aubrey |
E139743
|
entity |
| Predicate | hasFriendshipType |
P10690
|
FINISHED |
| Object | ship's surgeon–captain friendship |
—
|
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: ship's surgeon–captain friendship | Statement: [Jack Aubrey, hasFriendshipType, ship's surgeon–captain friendship]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFriendshipType Context triple: [Jack Aubrey, hasFriendshipType, ship's surgeon–captain friendship]
-
A.
hasFriendship
Indicates a mutual, positive social relationship of friendship existing between two entities.
-
B.
hasPartnershipType
Indicates the specific kind or category of partnership relationship that exists between entities.
-
C.
relationshipType
chosen
Indicates the specific kind of relationship that exists between two or more entities.
-
D.
hasContactType
Indicates the specific kind or category of contact relationship that exists between two entities.
-
E.
companionshipStatus
Indicates the current state or condition of a relationship of companionship between two or more entities.
- 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_69c008b1c5088190ae6de2555fc05ad8 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0631f511c81908d413320efdce42e |
completed | March 22, 2026, 9:46 p.m. |
| PD | Predicate disambiguation | batch_69c056037bf88190a0a3fe7429345d0b |
completed | March 22, 2026, 8:50 p.m. |
Created at: March 22, 2026, 4:23 p.m.