Triple
T4303576
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hippo Regius |
E99898
|
entity |
| Predicate | wasPortFor |
P1763
|
FINISHED |
| Object | Mediterranean trade |
—
|
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: Mediterranean trade | Statement: [Hippo Regius, wasPortFor, Mediterranean trade]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasPortFor Context triple: [Hippo Regius, wasPortFor, Mediterranean trade]
-
A.
hasPortOn
Indicates that one entity possesses or is located adjacent to a port situated on another specified geographic or infrastructural feature (such as a coast, river, or lake).
-
B.
port
chosen
Indicates a relationship where one entity serves as a harbor, access point, or interface through which another entity can enter, exit, or connect.
-
C.
usedOnPort
Indicates that something is applied, connected, or operates specifically on a given port.
-
D.
portAlsoKnownAs
Indicates that a port is referred to by an alternative name or alias.
-
E.
registeredPort
Indicates that a specific network port number has been officially assigned and recorded for use by a particular service or protocol.
- 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_69b345528ebc8190b5abc7e95094792d |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b350b792608190ac778b79c740256a |
completed | March 12, 2026, 11:48 p.m. |
| PD | Predicate disambiguation | batch_69b347ff45cc8190b0cc335a94cc3d73 |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:08 p.m.