Triple
T22585082
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unicode bidirectional algorithm |
E564766
|
entity |
| Predicate | usesControlCharacter |
P23703
|
FINISHED |
| Object | LEFT-TO-RIGHT MARK (LRM) |
—
|
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: LEFT-TO-RIGHT MARK (LRM) | Statement: [Unicode bidirectional algorithm, usesControlCharacter, LEFT-TO-RIGHT MARK (LRM)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesControlCharacter Context triple: [Unicode bidirectional algorithm, usesControlCharacter, LEFT-TO-RIGHT MARK (LRM)]
-
A.
hasCharacterControl
Indicates that one entity has the ability or authority to direct, manipulate, or govern the behavior or state of another entity.
-
B.
hasControlCharacterRange
chosen
Indicates that there exists a specified range of control characters associated with or applicable to an entity.
-
C.
hasSpecialCharacter
Indicates that a given entity (such as a string or identifier) contains at least one non-alphanumeric special character.
-
D.
usesCharactersAs
Indicates that one entity employs or incorporates specific characters (such as letters, symbols, or glyphs) from another entity for its representation or functioning.
-
E.
usedControl
Indicates that one entity exercised or applied a control mechanism or method over another entity or process.
- 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_69e245836014819091b91ed3074742a3 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f1615c18f88190ad4f23639d15f337 |
completed | April 29, 2026, 1:39 a.m. |
| PD | Predicate disambiguation | batch_69ee626e6bb08190ada4dd8b48cc0c43 |
completed | April 26, 2026, 7:07 p.m. |
Created at: April 17, 2026, 2:45 p.m.