Triple
T26641062
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ยี่เป็ง |
E668779
|
entity |
| Predicate | จัดขึ้นพร้อมกับ |
P69617
|
FINISHED |
| Object | เทศกาลลอยกระทง |
—
|
NE NERFINISHED |
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: เทศกาลลอยกระทง | Statement: [ยี่เป็ง, จัดขึ้นพร้อมกับ, เทศกาลลอยกระทง]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: จัดขึ้นพร้อมกับ Context triple: [ยี่เป็ง, จัดขึ้นพร้อมกับ, เทศกาลลอยกระทง]
-
A.
convenesAlongside
chosen
Indicates that one event, meeting, or session is held at the same time and in coordination with another, typically as a parallel or accompanying gathering.
-
B.
executedAlongWith
Indicates that one entity was carried out, performed, or implemented in conjunction with another entity, at the same time or as part of the same operation or event.
-
C.
preparesWith
Indicates that one entity is used as a means, tool, or method by which another entity is prepared or made ready.
-
D.
organisedWith
Indicates that two or more entities are arranged, coordinated, or structured together as part of the same organizing context or effort.
-
E.
formedTogetherWith
Indicates that two or more entities were created, established, or brought into existence at the same time or as part of the same formation process.
- 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_69ee9d0024b8819090a7c8cf669a3b6c |
completed | April 26, 2026, 11:17 p.m. |
| NER | Named-entity recognition | batch_69f6383625cc8190aa223d8ef655743c |
completed | May 2, 2026, 5:45 p.m. |
| PD | Predicate disambiguation | batch_69f63709e4848190b5cf322e06b23fb6 |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 27, 2026, 2:29 a.m.