Triple
T7348048
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miqat |
E169426
|
entity |
| Predicate | YalamlamFor |
P76733
|
FINISHED |
| Object | people coming from Yemen or that direction |
—
|
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: people coming from Yemen or that direction | Statement: [Miqat, YalamlamFor, people coming from Yemen or that direction]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: YalamlamFor Context triple: [Miqat, YalamlamFor, people coming from Yemen or that direction]
-
A.
yonMeans
Indicates that one entity serves as the meaning, definition, or semantic content of another entity.
-
B.
lays
Indicates that one entity deposits or places something, typically eggs or objects, onto a surface or in a location.
-
C.
by
Indicates that an action is performed, caused, or authored through the agency, means, or proximity of a specified entity.
-
D.
wand
Indicates that one entity uses or possesses a wand as an instrument or tool in relation to another entity or action.
-
E.
givenFor
Indicates that something is provided, offered, or assigned in favor of or on behalf of a particular entity or purpose.
- 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_69c68a5878888190968ce4d04db8d69f |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f139505c8190a7158cf59a6e089e |
completed | March 27, 2026, 9:06 p.m. |
| PD | Predicate disambiguation | batch_69c6f02aeeb8819099d1626566cec18b |
completed | March 27, 2026, 9:01 p.m. |
| PDg | Predicate description generation | batch_69c6f1379cac81908b35e617c44c7b13 |
completed | March 27, 2026, 9:05 p.m. |
Created at: March 27, 2026, 3:05 p.m.