Triple
T30965785
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Celeste |
E788952
|
entity |
| Predicate | cargoQuantity |
P170855
|
FINISHED |
| Object | about 1,701 barrels of alcohol |
—
|
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: about 1,701 barrels of alcohol | Statement: [Mary Celeste, cargoQuantity, about 1,701 barrels of alcohol]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cargoQuantity Context triple: [Mary Celeste, cargoQuantity, about 1,701 barrels of alcohol]
-
A.
cargoContents
Indicates that one entity contains or carries another entity as its cargo.
-
B.
cargoLoading
Indicates the action or process of placing cargo onto a vehicle, vessel, or other transport medium for shipment or movement.
-
C.
cargoMassDelivered
Indicates that a certain mass of cargo has been successfully transported and delivered from a source to a destination.
-
D.
cargoSpace
Indicates that one entity provides storage capacity or room for carrying goods, equipment, or other items for another entity.
-
E.
cargoHoldType
Indicates the specific type or classification of a cargo hold associated with an 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_69f224c3a6b48190951add9b7b7f0271 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f695f9fe7c819084322bf6cdc70a13 |
completed | May 3, 2026, 12:25 a.m. |
| PD | Predicate disambiguation | batch_69f690ef92308190903a54fc74233269 |
completed | May 3, 2026, 12:03 a.m. |
| PDg | Predicate description generation | batch_69f695385a2881908cc28ef97fffc867 |
completed | May 3, 2026, 12:22 a.m. |
Created at: April 29, 2026, 8:54 p.m.