Triple
T29357739
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guanghe |
E744491
|
entity |
| Predicate | startYearInEasternHan |
P196781
|
FINISHED |
| Object | Emperor Ling, 1st year of Guanghe (178) |
—
|
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: Emperor Ling, 1st year of Guanghe (178) | Statement: [Guanghe, startYearInEasternHan, Emperor Ling, 1st year of Guanghe (178)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startYearInEasternHan Context triple: [Guanghe, startYearInEasternHan, Emperor Ling, 1st year of Guanghe (178)]
-
A.
startYearInChineseCalendar
Indicates the year, expressed in the Chinese calendar system, when something (such as an event, period, or entity’s existence) begins.
-
B.
startEraInJapaneseCalendar
Indicates the point in time when a specific era begins within the Japanese calendar system.
-
C.
eraStartYearBC
Indicates the year (counting backward from year 1) in which a particular era or period begins, expressed in the BC (Before Christ/BCE) dating system.
-
D.
startOfEdoPeriod
Indicates that something marks the beginning or initial phase of the Edo period in Japanese history.
-
E.
eraStartHeiseiYear
Indicates the calendar year in which the Heisei era begins for a given context or system of dating.
- 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_69f0a79aee588190b490f19d93c6e52d |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_69fe68a4b67881909ca1d9f276f922e0 |
completed | May 8, 2026, 10:50 p.m. |
| PD | Predicate disambiguation | batch_69fe680234c88190b01f953987b74972 |
completed | May 8, 2026, 10:47 p.m. |
| PDg | Predicate description generation | batch_69fe68a385f48190b942700e3eddc9b6 |
completed | May 8, 2026, 10:50 p.m. |
Created at: April 28, 2026, 2:14 p.m.