Triple
T17143865
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pulilan |
E416038
|
entity |
| Predicate | festivalMainAttraction |
P96461
|
FINISHED |
| Object | kneeling carabaos |
—
|
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: kneeling carabaos | Statement: [Pulilan, festivalMainAttraction, kneeling carabaos]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: festivalMainAttraction Context triple: [Pulilan, festivalMainAttraction, kneeling carabaos]
-
A.
festivalAttracts
Indicates that a festival draws or brings in attendees, participants, or interest toward itself.
-
B.
mainFestival
Indicates that an event is the primary or central festival associated with a particular context, place, or entity.
-
C.
festivalFeature
chosen
Indicates that a festival includes or showcases a particular element, activity, or attraction as one of its features.
-
D.
mainFestivalDay
Indicates that a particular day is the primary or most significant day within a festival’s overall schedule.
-
E.
festivalFocus
Indicates that a festival is centered around, dedicated to, or thematically focused on a particular subject, activity, or feature.
- 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_69d886d15af4819092f92f8a129763e6 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3f2d8ca8c81909bba0cd6d60a4776 |
completed | April 18, 2026, 9:08 p.m. |
| PD | Predicate disambiguation | batch_69e3830192ac819091344a9e5a36c8c9 |
completed | April 18, 2026, 1:11 p.m. |
Created at: April 10, 2026, 5:36 a.m.