Triple
T651648
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shield of David |
E11356
|
entity |
| Predicate | hasUnicode |
P16918
|
FINISHED |
| Object | U+2721 |
—
|
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: U+2721 | Statement: [Shield of David, hasUnicode, U+2721]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasUnicode Context triple: [Shield of David, hasUnicode, U+2721]
-
A.
hasUnicodeStatus
Indicates that a given entity has a particular Unicode-related classification or status (such as assigned, reserved, deprecated, or noncharacter) within the Unicode standard.
-
B.
hasUnicodeName
Indicates that an entity is associated with a specific official Unicode name assigned to a character or symbol.
-
C.
hasUnicodeScript
Indicates that a character or text element belongs to a specific Unicode script category (such as Latin, Cyrillic, or Han).
-
D.
hasAccent
Indicates that an entity speaks with or possesses a particular accent or distinctive pronunciation style.
-
E.
hasCombiningMarks
Indicates that an entity (such as a character or string) includes one or more combining marks attached to a base element.
- 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_69a493266a2881909daf4c40f719dee8 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49f35acb08190a3a8248023ce07f9 |
completed | March 1, 2026, 8:19 p.m. |
| PD | Predicate disambiguation | batch_69a49d1001088190aa7ca3c8f2ad0e32 |
completed | March 1, 2026, 8:09 p.m. |
| PDg | Predicate description generation | batch_69a49dc0e6a08190b81d82a6f2571c41 |
completed | March 1, 2026, 8:12 p.m. |
Created at: March 1, 2026, 7:36 p.m.