Triple
T6161651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U.S. Army Berlin Brigade |
E137455
|
entity |
| Predicate | maintainedPresence |
P69132
|
FINISHED |
| Object | behind the Iron Curtain |
—
|
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: behind the Iron Curtain | Statement: [U.S. Army Berlin Brigade, maintainedPresence, behind the Iron Curtain]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maintainedPresence Context triple: [U.S. Army Berlin Brigade, maintainedPresence, behind the Iron Curtain]
-
A.
onlinePresence
Indicates that an entity maintains a presence or representation on the internet, such as through websites, profiles, or digital platforms.
-
B.
modernPresence
Indicates that something exists, appears, or is active in the contemporary or present-day context.
-
C.
globalPresence
Indicates that an entity operates, is represented, or has a significant footprint across multiple countries or world regions.
-
D.
statePresence
Indicates that an entity exists, operates, or is present within a particular state or governmental jurisdiction.
-
E.
hasHumanPresence
Indicates that humans are physically present in or occupying a given location, object, or context.
- F. None of above. chosen
Provenance (4 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_69c008a54fc88190b6ce4416490ca79d |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c05d371484819090c18b62b095b49e |
completed | March 22, 2026, 9:20 p.m. |
| PD | Predicate disambiguation | batch_69c055f5b81481908819515cdc334ae6 |
completed | March 22, 2026, 8:49 p.m. |
| PDg | Predicate description generation | batch_69c056df95ac8190bc5efe050d3af864 |
completed | March 22, 2026, 8:53 p.m. |
Created at: March 22, 2026, 4:17 p.m.