Triple
T29749831
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FÉLIN soldier system |
E752862
|
entity |
| Predicate | fieldedTo |
P115677
|
FINISHED |
| Object | French infantry regiments |
—
|
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: French infantry regiments | Statement: [FÉLIN soldier system, fieldedTo, French infantry regiments]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fieldedTo Context triple: [FÉLIN soldier system, fieldedTo, French infantry regiments]
-
A.
fieldedIn
chosen
Indicates that an entity was deployed, presented, or put into active use within a particular context, event, or domain.
-
B.
fielded
Indicates that an entity deployed, presented, or put forward another entity (such as a person, team, or resource) for participation or use in a particular context or activity.
-
C.
fieldedCombinedTeamIn
Indicates that an entity organized and presented a joint or composite team to participate in a specified event or context.
-
D.
finalOutFielder
Indicates that the specified player is the outfielder who records the final defensive out in a play or game.
-
E.
fieldingAbility
Indicates the level or quality of an entity’s skill and effectiveness in performing fielding actions in a game or sport.
- 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_69f0d62c84cc8190846f80ae04fdf8ec |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f6bbf6e33c819086e5176d64e7a614 |
completed | May 3, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6b1e6c8190adf9d6a257e0b744 |
completed | May 3, 2026, 3 a.m. |
Created at: April 28, 2026, 7:53 p.m.