Triple
T7156496
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jazirat al-Tair |
E166823
|
entity |
| Predicate | shippingRisk |
P75192
|
FINISHED |
| Object | navigation hazard during eruptions |
—
|
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: navigation hazard during eruptions | Statement: [Jazirat al-Tair, shippingRisk, navigation hazard during eruptions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shippingRisk Context triple: [Jazirat al-Tair, shippingRisk, navigation hazard during eruptions]
-
A.
protectsShippingTo
Indicates that one entity safeguards or ensures the security of shipping or delivery directed toward another entity.
-
B.
shippingFunction
Indicates the method or process by which goods are transported or delivered from a sender to a recipient.
-
C.
stateShip
Indicates that a ship is officially registered, documented, or associated with a particular state or governmental authority.
-
D.
logisticsFeature
Indicates that something possesses a characteristic, capability, or function specifically related to logistics operations or processes.
-
E.
hasPassengerShipping
Indicates that one entity provides or is involved in passenger shipping services or transport for another entity.
- 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_69c68887a5cc8190bec0ea96227164f7 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e80dafdc8190b24863b83f084d12 |
completed | March 27, 2026, 8:26 p.m. |
| PD | Predicate disambiguation | batch_69c6e1cd5c948190a9113b23f7308c21 |
completed | March 27, 2026, 8 p.m. |
| PDg | Predicate description generation | batch_69c6e4a213508190a40aca39f9eee7d5 |
completed | March 27, 2026, 8:12 p.m. |
Created at: March 27, 2026, 2:47 p.m.