Triple
T5488794
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Avestan script |
E123648
|
entity |
| Predicate | hasSpecialSignFor |
P9766
|
FINISHED |
| Object | word separation |
—
|
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: word separation | Statement: [Avestan script, hasSpecialSignFor, word separation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpecialSignFor Context triple: [Avestan script, hasSpecialSignFor, word separation]
-
A.
hasSpecial
Indicates that an entity possesses or is associated with a distinctive or exceptional attribute, status, or feature compared to others.
-
B.
hasSpecialCharacter
Indicates that a given entity (such as a string or identifier) contains at least one non-alphanumeric special character.
-
C.
hasSign
chosen
Indicates that an entity possesses, displays, or is associated with a particular sign or symbol.
-
D.
hasSpecials
Indicates that an entity offers or is associated with special deals, promotions, or limited-time offers.
-
E.
hasSpecialCategory
Indicates that an entity is associated with a designated special or exceptional category distinct from its standard classifications.
- 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_69bd464a2d908190869324ce176779c8 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd93e5d0f08190a6cc9fc408b7c5bb |
completed | March 20, 2026, 6:37 p.m. |
| PD | Predicate disambiguation | batch_69bd91a73b148190a865243536a4fe76 |
completed | March 20, 2026, 6:27 p.m. |
Created at: March 20, 2026, 2:10 p.m.