Triple
T7073181
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pongal |
E164749
|
entity |
| Predicate | monthInTamilCalendar |
P74840
|
FINISHED |
| Object | Thai |
—
|
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: Thai | Statement: [Pongal, monthInTamilCalendar, Thai]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: monthInTamilCalendar Context triple: [Pongal, monthInTamilCalendar, Thai]
-
A.
monthOfBengaliCalendar
Indicates that one entity specifies the month associated with a date or event according to the Bengali calendar.
-
B.
monthInHinduCalendar
Indicates that a specified time or event falls within a particular month as defined by the Hindu calendar system.
-
C.
monthNumber
Indicates the numerical position of a month within a calendar year (e.g., January = 1, February = 2, etc.).
-
D.
monthInHebrewCalendar
Indicates that one entity is a specific month as defined in the Hebrew calendar system in relation to another entity.
-
E.
monthName2
Indicates that two entities are associated as the same calendar month, where one provides the month’s name and the other represents that month in another form (such as a number or date).
- 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_69c6887b96548190a8a9b3ac8adf4119 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e4cb76548190bd98876f8ba925b7 |
completed | March 27, 2026, 8:12 p.m. |
| PD | Predicate disambiguation | batch_69c6e1bfcb948190a5ada74fb8c054cb |
completed | March 27, 2026, 8 p.m. |
| PDg | Predicate description generation | batch_69c6e4a15b088190bee9a23e94aaac53 |
completed | March 27, 2026, 8:12 p.m. |
Created at: March 27, 2026, 2:39 p.m.