Triple
T16168754
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blemmyes |
E392376
|
entity |
| Predicate | possiblySpoke |
P66153
|
FINISHED |
| Object | early Cushitic language |
—
|
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: early Cushitic language | Statement: [Blemmyes, possiblySpoke, early Cushitic language]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: possiblySpoke Context triple: [Blemmyes, possiblySpoke, early Cushitic language]
-
A.
possiblySpokenAt
chosen
Indicates that an utterance or speech event may have occurred at a particular time or location, but this association is uncertain or not definitively confirmed.
-
B.
hasSpokenAbout
Indicates that one entity has verbally expressed, discussed, or mentioned another entity or topic.
-
C.
isSpoken
Indicates that a language or utterance is produced orally by a speaker or used in spoken form within a given context.
-
D.
spokenUntil
Indicates that an act of speaking or verbal communication continues up to a specific time or event and then stops.
-
E.
sometimesSpeaks
Indicates that one entity speaks to or communicates with another only on some occasions, rather than regularly or consistently.
- 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_69d87f1d32208190942e4e499a80c18c |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e21eb5e6d881908749683091afa90c |
completed | April 17, 2026, 11:51 a.m. |
| PD | Predicate disambiguation | batch_69e219d642708190ba31a90dce76a210 |
completed | April 17, 2026, 11:30 a.m. |
Created at: April 10, 2026, 5:02 a.m.