Triple
T28302207
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John the Good |
E713738
|
entity |
| Predicate | wasCapturedAt |
P3419
|
FINISHED |
| Object | Battle of Poitiers |
—
|
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: Battle of Poitiers | Statement: [John the Good, wasCapturedAt, Battle of Poitiers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasCapturedAt Context triple: [John the Good, wasCapturedAt, Battle of Poitiers]
-
A.
capturedAt
Indicates the specific time or moment at which an entity was captured, recorded, or taken.
-
B.
wasRecapturedBy
Indicates that an entity which had previously escaped or been released was caught again by another entity.
-
C.
capturedDuring
chosen
Indicates that one event or state occurred within the temporal span of another, typically representing that something was recorded, seized, or documented while a specific situation or activity was taking place.
-
D.
capturedAfter
Indicates that one entity is captured at a point in time later than the capture of another entity.
-
E.
capturedBy
Indicates that one entity has been seized, taken into control, or otherwise apprehended by another entity.
- 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_69efb524ab688190a1ce7ee7c9520932 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f644b3c6088190b3a20e8916fcddba |
completed | May 2, 2026, 6:38 p.m. |
| PD | Predicate disambiguation | batch_69f641e0fde08190bf06a1c5b388aa84 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 27, 2026, 11:35 p.m.