Triple
T15902916
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Myanmar Era |
E385632
|
entity |
| Predicate | eraStartYearGregorianApprox |
P13193
|
FINISHED |
| Object | 638 |
—
|
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: 638 | Statement: [Myanmar Era, eraStartYearGregorianApprox, 638]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eraStartYearGregorianApprox Context triple: [Myanmar Era, eraStartYearGregorianApprox, 638]
-
A.
approximateStartYear
chosen
Indicates that the associated year value represents an estimated or imprecise starting year for an event, state, or relationship rather than an exact one.
-
B.
beganInYear
Indicates that an event, process, or state started in a specific calendar year.
-
C.
endYearApprox
Indicates that the end year of an event, state, or relationship is known only approximately rather than as a precise calendar year.
-
D.
estimatedYearOfCreation
Indicates the year in which something is believed or approximated to have been created, rather than a precisely known creation year.
-
E.
originYear
Indicates the year in which something first originated, was created, or began.
- 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_69d86da5b800819083a31be937d738b0 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e17d4d08f481909f38b75e3f42d9ab |
completed | April 17, 2026, 12:22 a.m. |
| PD | Predicate disambiguation | batch_69e142ca3b208190946c3aa4c1e6087c |
completed | April 16, 2026, 8:12 p.m. |
Created at: April 10, 2026, 4:52 a.m.