Triple
T37954007
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fancy Sailor |
E946813
|
entity |
| Predicate | hasCostumeCharacteristic |
P58290
|
FINISHED |
| Object | exaggerated naval costume |
—
|
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: exaggerated naval costume | Statement: [Fancy Sailor, hasCostumeCharacteristic, exaggerated naval costume]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCostumeCharacteristic Context triple: [Fancy Sailor, hasCostumeCharacteristic, exaggerated naval costume]
-
A.
hasCostumeBrand
Indicates that an entity’s costume is associated with or produced by a particular brand.
-
B.
hasCostumesFrom
Indicates that one entity possesses or includes costumes that originate from, are inspired by, or are associated with another entity.
-
C.
haveDistinctCostume
Indicates that the entities each possess a costume that is different from the others’ costumes.
-
D.
hasCostumes
Indicates that one entity possesses, provides, or is associated with one or more costumes.
-
E.
costumeFeatures
chosen
Indicates that a costume possesses or includes specific features, attributes, or decorative elements.
- 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_69f76ef64cf08190ad3e1114b62aac67 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a037c903be48190a2fafa53d7d50d42 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a192a008190a9917688a9e804f4 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:20 p.m.