Triple
T31491846
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gädl of Saint Lalibela |
E803426
|
entity |
| Predicate | associatedFeastDay |
P207439
|
FINISHED |
| Object | feast of Saint Lalibela |
—
|
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: feast of Saint Lalibela | Statement: [Gädl of Saint Lalibela, associatedFeastDay, feast of Saint Lalibela]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedFeastDay Context triple: [Gädl of Saint Lalibela, associatedFeastDay, feast of Saint Lalibela]
-
A.
majorFeast
Indicates that an event or celebration is recognized as a major religious or cultural feast of high importance.
-
B.
sharesFeastDayWith
Indicates that two entities are commemorated or celebrated on the same feast day in a liturgical or religious calendar.
-
C.
feastDayAlsoKnownAs
Indicates that a religious or commemorative feast day is referred to by an alternative name or title.
-
D.
feastDayObservedOn
Indicates that a particular feast day is celebrated or formally observed on a specified calendar date.
-
E.
institutedFeast
Indicates that an authority or group formally established and put into practice a particular feast or festival as an ongoing observance.
- 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_69f348ca04508190ba9379b5329dfd75 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_6a037c9141dc819098d7fcc36e69882c |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379e7aa0c8190bdc9ee4d54fc821b |
completed | May 12, 2026, 7:05 p.m. |
| PDg | Predicate description generation | batch_6a037c7ee0388190a29faeb5cdb0950a |
completed | May 12, 2026, 7:16 p.m. |
Created at: April 30, 2026, 9:38 p.m.