Triple
T14472978
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isle of Eight Flags Shrimp Festival |
E358890
|
entity |
| Predicate | hasCraftType |
P114787
|
FINISHED |
| Object | handmade arts and crafts |
—
|
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: handmade arts and crafts | Statement: [Isle of Eight Flags Shrimp Festival, hasCraftType, handmade arts and crafts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCraftType Context triple: [Isle of Eight Flags Shrimp Festival, hasCraftType, handmade arts and crafts]
-
A.
hasCraft
Indicates a relationship where an entity possesses, operates, or is associated with a particular vehicle, vessel, or other craft.
-
B.
hasCraftVillageType
Indicates that an entity is associated with, or classified by, a specific type or category of craft village.
-
C.
hasCeramicsType
Indicates that an entity is associated with or classified by a specific type or category of ceramics.
-
D.
hasCarvingType
Indicates that one entity is associated with a specific type or style of carving applied to it.
-
E.
hasCraftsman
Indicates that one entity serves as the craftsman, maker, or artisan responsible for creating, building, or crafting another entity.
- F. None of above. chosen
Provenance (4 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_69d827966698819082e140837737501d |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de91fab21c819090b6e209d8efba6e |
completed | April 14, 2026, 7:14 p.m. |
| PD | Predicate disambiguation | batch_69de5c42bd3c81909a62acf30cc24d1e |
completed | April 14, 2026, 3:24 p.m. |
| PDg | Predicate description generation | batch_69de610330a48190b558235a14c0dc9f |
completed | April 14, 2026, 3:45 p.m. |
Created at: April 10, 2026, 1:20 a.m.