Triple
T12939376
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Kyzikos (c. 677) |
E309596
|
entity |
| Predicate | hasApproximateYear |
P877
|
FINISHED |
| Object | 677 |
—
|
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: 677 | Statement: [Battle of Kyzikos (c. 677), hasApproximateYear, 677]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasApproximateYear Context triple: [Battle of Kyzikos (c. 677), hasApproximateYear, 677]
-
A.
retitleApproxYear
Indicates that an entity was retitled or renamed around an approximate year, rather than at a precisely known date.
-
B.
dateApproximate
chosen
Indicates that the associated date is not exact but estimated or approximate rather than precisely known.
-
C.
approximateStartYear
Indicates that the associated year value represents an estimated or imprecise starting year for an event, state, or relationship rather than an exact one.
-
D.
releaseApproximateYear
Indicates that an entity was released or made available around a specified year, where the year is approximate rather than exact.
-
E.
yearCirca
Indicates that the associated year is approximate or uncertain rather than exact.
- 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_69d7bdfa933c8190b5a27aa4a08a19b7 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97e59a4c88190907d05b8d57dae89 |
completed | April 10, 2026, 10:48 p.m. |
| PD | Predicate disambiguation | batch_69d97db69f548190a1a693bc0d6c191a |
completed | April 10, 2026, 10:46 p.m. |
Created at: April 9, 2026, 5:43 p.m.