Triple
T5222160
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alpha Phi Alpha |
E117893
|
entity |
| Predicate | hasGreekLetters |
P3659
|
FINISHED |
| Object | ΑΦΑ |
—
|
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: ΑΦΑ | Statement: [Alpha Phi Alpha, hasGreekLetters, ΑΦΑ]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGreekLetters Context triple: [Alpha Phi Alpha, hasGreekLetters, ΑΦΑ]
-
A.
hasNameInGreek
chosen
Indicates that an entity is associated with a specific representation of its name in the Greek language.
-
B.
hasGreekCounterpartGroup
Indicates that something is associated with a corresponding group or set of counterparts in the context of Greek tradition or classification.
-
C.
hasTitleInGreek
Indicates that an entity possesses a specific title expressed in the Greek language.
-
D.
correspondsToGreekLetter
Indicates that something is associated with, represents, or is equivalent to a specific letter of the Greek alphabet.
-
E.
hasGreekLife
Indicates that an institution or organization offers or supports Greek-letter fraternities and/or sororities.
- 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_69bd4465e03081909bfcfd7113062590 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7aba05b48190b6a7fc52ab3532f0 |
completed | March 20, 2026, 4:50 p.m. |
| PD | Predicate disambiguation | batch_69bd77bd2a448190a9ae5afd2585a7b9 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:48 p.m.