Triple
T14490835
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deendayal Port Authority |
E359356
|
entity |
| Predicate | typeOfPortManaged |
P16380
|
FINISHED |
| Object | commercial seaport |
—
|
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: commercial seaport | Statement: [Deendayal Port Authority, typeOfPortManaged, commercial seaport]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfPortManaged Context triple: [Deendayal Port Authority, typeOfPortManaged, commercial seaport]
-
A.
typeOfPropertyManaged
Indicates the specific category or kind of property that an entity is responsible for managing.
-
B.
portManagedBy
Indicates that the operation, administration, or control of a port is carried out by a specified managing entity.
-
C.
typeOfPortFacility
Indicates that one port facility is classified as a specific type or category of port facility in relation to another.
-
D.
hasPortType
chosen
Indicates that an entity is associated with, or characterized by, a specific type or category of port.
-
E.
typeOfEquipmentManaged
Indicates the specific kind or category of equipment that an entity is responsible for managing.
- 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_69d8279740308190af9df93a3af8592e |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de930d820481908b9813014dd02540 |
completed | April 14, 2026, 7:18 p.m. |
| PD | Predicate disambiguation | batch_69de5c487b4c819097803e58dca628a5 |
completed | April 14, 2026, 3:24 p.m. |
Created at: April 10, 2026, 1:20 a.m.