Triple
T11564323
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shivta |
E274215
|
entity |
| Predicate | tradingRoute |
P35626
|
FINISHED |
| Object | incense trade route |
—
|
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: incense trade route | Statement: [Shivta, tradingRoute, incense trade route]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tradingRoute Context triple: [Shivta, tradingRoute, incense trade route]
-
A.
includesTradeRoute
chosen
Indicates that one entity contains, encompasses, or makes use of a particular trade route within its scope or structure.
-
B.
tradRoutes
Indicates a relationship where one location serves as a trade route to or from another location, facilitating the movement of goods or commerce between them.
-
C.
tradingApproach
Indicates the method or strategy an entity uses to conduct trading activities or make trade-related decisions.
-
D.
tradingSegment
Indicates that one entity operates within, or is associated with, a specific trading segment or market subdivision for transactional activities.
-
E.
tradingLinks
Indicates that there are established trade or commercial exchange relationships between the referenced entities.
- 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_69d6aae5ac3c81908d2b0a3a665665b2 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d88dd321f88190a57ecaf079fbbc3f |
completed | April 10, 2026, 5:42 a.m. |
| PD | Predicate disambiguation | batch_69d85dc3fc2c8190bed7e2111301a77c |
completed | April 10, 2026, 2:17 a.m. |
Created at: April 8, 2026, 9:37 p.m.