Triple
T27637655
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mustache |
E696509
|
entity |
| Predicate | templateDelimiter |
P86777
|
FINISHED |
| Object | {{ |
—
|
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: {{ | Statement: [Mustache, templateDelimiter, {{]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: templateDelimiter
Context triple: [Mustache, templateDelimiter, {{]
-
A.
blockDelimiter
Indicates that one entity serves as a boundary marker that starts, ends, or separates a logical block associated with another entity.
-
B.
alternativeDelimiters
Indicates a relationship where one or more substitute boundary markers are used in place of the primary delimiters for separating or enclosing elements.
-
C.
postDelimitation
Indicates that the related action, status, or condition occurs after a specified boundary, cutoff point, or delimiting event.
-
D.
separators
chosen
Indicates that one entity divides, distinguishes, or creates a boundary between two or more other entities.
-
E.
supportsDelimiterVariation
Indicates that one entity is capable of handling or accommodating different types or formats of delimiters used by another entity.
- 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_69ef5909f3848190805f35b76833e722 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f6318e4c9c8190960df19eed7546fa |
completed | May 2, 2026, 5:17 p.m. |
| PD | Predicate disambiguation | batch_69f62c1921008190a62675a31f66a875 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:24 p.m.