Triple
T35604285
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TT-Line Company |
E1028841
|
entity |
| Predicate | operatesVesselBrand |
P13018
|
FINISHED |
| Object | Spirit of Tasmania |
—
|
NE NERFINISHED |
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: Spirit of Tasmania | Statement: [TT-Line Company, operatesVesselBrand, Spirit of Tasmania]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatesVesselBrand Context triple: [TT-Line Company, operatesVesselBrand, Spirit of Tasmania]
-
A.
operatesVessel
chosen
Indicates that an agent is responsible for controlling, managing, or running the operation of a vessel.
-
B.
usesVesselsOperatedBy
Indicates that one entity makes use of vessels that are operated or controlled by another entity.
-
C.
vesselTypeServedOn
Indicates the type of vessel on which an entity has served or performed duty.
-
D.
appliesToVesselName
Indicates that something (such as a rule, condition, or record) is specifically associated with or relevant to a particular vessel’s name.
-
E.
sponsoredVesselType
Indicates that one entity has provided sponsorship or financial backing specifically for a vessel of a given type.
- 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_69f76e0653ec81909b1b813c126c6574 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a014f7602988190b8f86cb431a9cf12 |
completed | May 11, 2026, 3:39 a.m. |
| PD | Predicate disambiguation | batch_6a014a70ea748190bd86fb9f218103ba |
completed | May 11, 2026, 3:18 a.m. |
Created at: May 3, 2026, 4:05 p.m.