Triple
T13936503
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bertilak's castle |
E335133
|
entity |
| Predicate | hasHospitalityCustom |
P77271
|
FINISHED |
| Object | lavish feasting |
—
|
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: lavish feasting | Statement: [Bertilak's castle, hasHospitalityCustom, lavish feasting]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHospitalityCustom Context triple: [Bertilak's castle, hasHospitalityCustom, lavish feasting]
-
A.
hasHospitalityComponent
Indicates that something includes, involves, or is associated with a hospitality-related element, service, or function.
-
B.
hasServingCustom
chosen
Indicates that an entity follows or applies a particular custom, style, or convention in how something (such as food, drink, or service) is served.
-
C.
hadCustom
Indicates that an entity previously possessed or was associated with a customized or user-defined version of something.
-
D.
hasHolidayCustom
Indicates that there is a specific traditional practice or custom associated with a particular holiday.
-
E.
hasPartnerHotel
Indicates that one hotel has an established partnership or affiliation relationship with another hotel.
- 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_69d81c5f739081908bc05b2461f54828 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2cf42878819085146670d7b92605 |
completed | April 14, 2026, 12:03 p.m. |
| PD | Predicate disambiguation | batch_69dbc873052c8190b33ff7f7c5a4e7ee |
completed | April 12, 2026, 4:29 p.m. |
Created at: April 9, 2026, 10:17 p.m.