Triple
T11164652
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Loy Krathong |
E264129
|
entity |
| Predicate | alternativeGregorianMonth |
P16936
|
FINISHED |
| Object | late October |
—
|
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: late October | Statement: [Loy Krathong, alternativeGregorianMonth, late October]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: alternativeGregorianMonth Context triple: [Loy Krathong, alternativeGregorianMonth, late October]
-
A.
monthObserved
Indicates the month during which an event, observation, or measurement took place.
-
B.
calendarMonthNameOrigin
Indicates the historical or cultural source from which a calendar month’s name is derived.
-
C.
correspondsRoughlyToGregorianMonths
chosen
Indicates that one or more time periods or units align approximately, but not exactly, with specific months in the Gregorian calendar.
-
D.
monthInIslamicCalendar
Indicates that one entity is a specific month within the Islamic (Hijri) calendar system.
-
E.
sacredMonthNumber
Indicates the numerical position or identifier assigned to a month that is considered sacred within a particular calendar or religious system.
- 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_69d6aa9ccddc8190868998c8b7beb060 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e887293081909830852000d533fa |
completed | April 9, 2026, 5:57 p.m. |
| PD | Predicate disambiguation | batch_69d75cec26fc8190a5497d186306f935 |
completed | April 9, 2026, 8:01 a.m. |
Created at: April 8, 2026, 9:29 p.m.