Triple
T32830894
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Argo |
E839686
|
entity |
| Predicate | hadFigurehead |
P76368
|
FINISHED |
| Object | speaking prow |
—
|
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: speaking prow | Statement: [Argo, hadFigurehead, speaking prow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadFigurehead Context triple: [Argo, hadFigurehead, speaking prow]
-
A.
wasFigureheadUnder
Indicates that one entity served as a nominal or symbolic leader (a figurehead) while being effectively controlled or directed by another entity.
-
B.
hadFort
Indicates that an entity possessed, controlled, or contained a fort at some time.
-
C.
hadStructure
chosen
Indicates that an entity possessed or was composed of a particular structural form, configuration, or physical arrangement.
-
D.
hasHeadOf
Indicates that one entity serves as the leader, chief, or person in charge of another entity (such as an organization, group, or department).
-
E.
hadModel
Indicates that an entity possessed, used, or was associated with a particular model (e.g., a product, design, or version) at some point in time.
- 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_69f3493f22f88190ae6dd4bc15b6cf8d |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6ce6d659881909ddcec1d2966e020 |
completed | May 3, 2026, 4:26 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1667a48190b42684f6ec22dae9 |
completed | May 3, 2026, 4:16 a.m. |
Created at: May 1, 2026, 1:16 a.m.