Triple
T19158829
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ħamrun |
E468996
|
entity |
| Predicate | hasLocalDay |
P105420
|
FINISHED |
| Object | feast day of St Cajetan in August |
—
|
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 day of St Cajetan in August | Statement: [Ħamrun, hasLocalDay, feast day of St Cajetan in August]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLocalDay Context triple: [Ħamrun, hasLocalDay, feast day of St Cajetan in August]
-
A.
hasLocalityDay
Indicates that a specific day is officially designated or observed within a particular locality or municipality.
-
B.
hasDayUnit
Indicates that something is measured, expressed, or quantified in units of days.
-
C.
hasDays
Indicates that an entity is associated with, spans, or occurs on specific days.
-
D.
hasLocalFeastMonth
chosen
Indicates that a particular location or community observes a local feast or festival during a specified month.
-
E.
hasPresentDayRegion
Indicates that an entity is currently located in, associated with, or falls within the boundaries of a specified modern-day geographic or administrative region.
- 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_69d8dd084ff48190ac0f8c46ee722629 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5eebb573081909fcd6af8aff8692b |
completed | April 20, 2026, 9:15 a.m. |
| PD | Predicate disambiguation | batch_69e4b9b83d6881908e6271c620f74100 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:06 p.m.