Triple
T26686729
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 5th New York Infantry (Duryee’s Zouaves) |
E672765
|
entity |
| Predicate | drillInfluence |
P152787
|
FINISHED |
| Object | French Army Zouave units |
—
|
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 Army Zouave units | Statement: [5th New York Infantry (Duryee’s Zouaves), drillInfluence, French Army Zouave units]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: drillInfluence Context triple: [5th New York Infantry (Duryee’s Zouaves), drillInfluence, French Army Zouave units]
-
A.
incorporatesInfluence
chosen
Indicates that one entity integrates or absorbs the influence, ideas, or characteristics of another into itself.
-
B.
ruleInfluence
Indicates that one rule affects, constrains, or modifies the behavior, outcome, or applicability of another rule.
-
C.
rulesInfluence
Indicates that one set of rules or regulations has an effect on, shapes, or constrains another entity, process, or outcome.
-
D.
influencedIn
Indicates that one entity had an effect on or shaped another entity within a specific context, domain, or setting.
-
E.
spinOffInfluence
Indicates that one entity has influenced the creation, direction, or characteristics of another entity that is derived from it as a spin-off.
- 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_69eecda2066c8190a344218afa5e89c1 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f6173e191481909d1f6691a6fa8396 |
completed | May 2, 2026, 3:24 p.m. |
| PD | Predicate disambiguation | batch_69f60b8bb0d08190ab5a9a2a8847c6f4 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 27, 2026, 3:23 a.m.