Triple
T134163
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Long Telegram |
E2714
|
entity |
| Predicate | authorPosition |
P938
|
FINISHED |
| Object | Chargé d’Affaires at the U.S. Embassy in Moscow |
—
|
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: Chargé d’Affaires at the U.S. Embassy in Moscow | Statement: [Long Telegram, authorPosition, Chargé d’Affaires at the U.S. Embassy in Moscow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: authorPosition Context triple: [Long Telegram, authorPosition, Chargé d’Affaires at the U.S. Embassy in Moscow]
-
A.
subjectPosition
Indicates the spatial or logical position of a subject relative to a reference frame, context, or other entities.
-
B.
authorOccupation
chosen
Indicates the professional role or job that an author holds or is associated with.
-
C.
namePosition
Indicates the positional or ordering relationship of a name within a sequence or structured context (e.g., first, last, or specific index).
-
D.
draftPosition
Indicates the selection order or specific pick at which an entity (such as a player) was chosen in a draft process.
-
E.
hasAuthor
Indicates that an entity is written or created by a specific author.
- 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_69a2520c0f3481908b0ed054a2fca8d0 |
completed | Feb. 28, 2026, 2:25 a.m. |
| NER | Named-entity recognition | batch_69a25788b2688190a45b39447f702551 |
completed | Feb. 28, 2026, 2:48 a.m. |
| PD | Predicate disambiguation | batch_69a25650251c81908a6ea6368cd61198 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:30 a.m.