Triple
T5967834
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Montmédy |
E132796
|
entity |
| Predicate | wasIntendedAs |
P32577
|
FINISHED |
| Object | royal refuge during Flight to Varennes |
—
|
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: royal refuge during Flight to Varennes | Statement: [Montmédy, wasIntendedAs, royal refuge during Flight to Varennes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasIntendedAs Context triple: [Montmédy, wasIntendedAs, royal refuge during Flight to Varennes]
-
A.
intendedMessage
Indicates that one entity is the message or content that another entity aims or plans to communicate.
-
B.
originalIntendedStatus
Indicates the status that was initially planned or expected for an entity before any changes or updates occurred.
-
C.
isSupposedToBe
chosen
Indicates that something is expected or intended to have a particular state, quality, or role, whether or not it actually does.
-
D.
wasA
Indicates that an entity previously had a certain role, type, or classification in the past.
-
E.
intendedFunction
Indicates that something is designed or purposed to perform a particular role, use, or function.
- 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_69c0086deab081908550159ca23eec9b |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c03e174c7c8190b04113f6529f5f0e |
completed | March 22, 2026, 7:08 p.m. |
| PD | Predicate disambiguation | batch_69c0335b55a48190927a5b1529edb542 |
completed | March 22, 2026, 6:22 p.m. |
Created at: March 22, 2026, 4:03 p.m.