Triple
T26061411
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jawf region of Yemen |
E657271
|
entity |
| Predicate | tradeCommodities |
P3553
|
FINISHED |
| Object | frankincense |
—
|
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: frankincense | Statement: [Jawf region of Yemen, tradeCommodities, frankincense]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tradeCommodities Context triple: [Jawf region of Yemen, tradeCommodities, frankincense]
-
A.
otherCommodity
Indicates that an entity is associated with a commodity that is different from a primary, specified, or expected commodity in the given context.
-
B.
productsTraded
Indicates that one entity exchanges or deals specific goods or commodities with another entity.
-
C.
commodityType
Indicates the classification of a good or product according to its type or category within a commodity system.
-
D.
commodity
chosen
Indicates that one entity is a tradable good or resource that is bought, sold, or exchanged in relation to another entity.
-
E.
tradeHubWith
Indicates that one entity functions as a central location or node for trading activities in connection with another entity.
- 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_69ee5bbd788481909e22bd7153d0c037 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f63fd6c68481908c542aa03e297b9c |
completed | May 2, 2026, 6:17 p.m. |
| PD | Predicate disambiguation | batch_69f63c6456608190b94e7c2e2c2a4824 |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 26, 2026, 7:18 p.m.