Triple
T26916540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | France Antarctique |
E677531
|
entity |
| Predicate | religiousGroupsInvolved |
P7903
|
FINISHED |
| Object | French Huguenots |
—
|
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: French Huguenots | Statement: [France Antarctique, religiousGroupsInvolved, French Huguenots]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: religiousGroupsInvolved Context triple: [France Antarctique, religiousGroupsInvolved, French Huguenots]
-
A.
religiousGroupsPresent
chosen
Indicates that one or more religious groups are present or represented in a given context, location, or situation.
-
B.
religiousGroupAffected
Indicates that a religious group is the one impacted, targeted, or otherwise affected by the referenced event, action, or condition.
-
C.
religiousGroupMentioned
Indicates that a religious group is referenced or mentioned in the given context or statement.
-
D.
religiousAlliance
Indicates a cooperative relationship formed between entities based on shared religious beliefs, institutions, or objectives.
-
E.
religiousEnvironment
Indicates the religious context, atmosphere, or setting in which an entity exists or an action takes place.
- 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_69eee9bdebc48190ba90a12a63e09c73 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f7aa699d68819081ed363931894ab3 |
completed | May 3, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69f7a8cec6d48190bebfa884b2f938c0 |
completed | May 3, 2026, 7:58 p.m. |
Created at: April 27, 2026, 6:04 a.m.