Triple
T10896720
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spring and Autumn Annals |
E257328
|
entity |
| Predicate | earliestEntryYear |
P44250
|
FINISHED |
| Object | 722 BC |
—
|
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: 722 BC | Statement: [Spring and Autumn Annals, earliestEntryYear, 722 BC]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: earliestEntryYear Context triple: [Spring and Autumn Annals, earliestEntryYear, 722 BC]
-
A.
beganInYear
Indicates that an event, process, or state started in a specific calendar year.
-
B.
firstSeriesYear
Indicates the year in which a series (such as a TV show, book series, or sports league season) first began or was initially released.
-
C.
inscriptionYearOfFirstElements
Indicates the year in which the first elements of something (such as a site, object, or collection) were officially inscribed or recorded in a designated register or list.
-
D.
recordStartYear
chosen
Indicates the calendar year in which a particular record, entry, or data instance first began or was created.
-
E.
firstRunningYear
Indicates the year in which something (such as an event, service, or operation) first began running or was initially active.
- 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_69d6aa8550c8819095508a2ed9acf3db |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d75d02e4c88190b8286078e90bf913 |
completed | April 9, 2026, 8:02 a.m. |
| PD | Predicate disambiguation | batch_69d70d3943c881908895397eccc3e415 |
completed | April 9, 2026, 2:21 a.m. |
Created at: April 8, 2026, 9:21 p.m.