Triple
T13228272
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bedford Flag |
E314936
|
entity |
| Predicate | allegedUseDate |
P52519
|
FINISHED |
| Object | April 19, 1775 |
—
|
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: April 19, 1775 | Statement: [Bedford Flag, allegedUseDate, April 19, 1775]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: allegedUseDate Context triple: [Bedford Flag, allegedUseDate, April 19, 1775]
-
A.
hasAllegedDate
Indicates that an entity is associated with a date that is claimed or reported, but not confirmed as certain.
-
B.
allegedUse
Indicates that something is claimed or suspected to have been used, without confirming that the use actually occurred.
-
C.
allegedDeedDate
Indicates the date on which a deed or action is claimed or reported to have occurred, without asserting that it actually took place.
-
D.
allegedInvolvementDate
chosen
Indicates the date on which an entity is claimed or reported to have been involved in a particular event or activity, without asserting that the involvement is confirmed.
-
E.
lastYearOfUse
Indicates the final year in which something was actively used or in operation.
- 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_69d806affc688190a25b6ccc588e9c72 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98d3232d48190a3c792b025c596a6 |
completed | April 10, 2026, 11:52 p.m. |
| PD | Predicate disambiguation | batch_69d98bcb21648190aef241de1e7887e2 |
completed | April 10, 2026, 11:46 p.m. |
Created at: April 9, 2026, 9:21 p.m.