Triple
T28011071
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Siege of Valenciennes (1677) |
E707419
|
entity |
| Predicate | countryAfterCapture |
P88267
|
FINISHED |
| Object | France |
—
|
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: France | Statement: [Siege of Valenciennes (1677), countryAfterCapture, France]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryAfterCapture Context triple: [Siege of Valenciennes (1677), countryAfterCapture, France]
-
A.
countryAfterIntegration
Indicates the country that exists as a result of, or following, an integration or unification process involving another entity.
-
B.
countryAfterConflict
chosen
Indicates that one country exists in a post-conflict state or status relative to a specified conflict or warring situation.
-
C.
countrySucceededBy
Indicates that one country is the direct successor state that replaces or follows another country in sovereignty or political continuity.
-
D.
countryAfterReplacement
Indicates that one country takes the place of another as a successor or replacement in a given context or role.
-
E.
placeOfRecapture
Indicates the location where an entity that had escaped or been released was subsequently captured again.
- 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_69ef96ba350c81908230d0b501b974c4 |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69fddac4e2f48190a9301d3422658b29 |
completed | May 8, 2026, 12:44 p.m. |
| PD | Predicate disambiguation | batch_69fdda06969c8190b5d033964ea2a690 |
completed | May 8, 2026, 12:41 p.m. |
Created at: April 27, 2026, 8:03 p.m.