Triple
T34383486
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Port of Valletta |
E882498
|
entity |
| Predicate | hasMaximumDraft |
P108511
|
FINISHED |
| Object | deep-water |
—
|
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: deep-water | Statement: [Port of Valletta, hasMaximumDraft, deep-water]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMaximumDraft Context triple: [Port of Valletta, hasMaximumDraft, deep-water]
-
A.
hasMaxDraftApprox
Indicates that one entity has, as an upper bound, an approximate maximum value or level for a draft-related quantity associated with another entity.
-
B.
maximumDraft
Indicates that there is an upper limit on the number of drafts that can be created, stored, or associated with a given entity or process.
-
C.
maxDraft
chosen
Indicates the maximum allowable or observed value of a draft (such as depth, airflow, or preliminary version) associated with an entity or process.
-
D.
hasDraft
Indicates that one entity possesses or is associated with a preliminary or unfinished version of another entity.
-
E.
hasDraftedPlayersTo
Indicates that one entity has selected or drafted players to join or belong to another entity, such as a team, league, or organization.
- 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_69f349c0219881909393bbbc1edc8161 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a01a18e350481909f848686568d19bc |
completed | May 11, 2026, 9:29 a.m. |
| PD | Predicate disambiguation | batch_6a01a121b67c81908a6c5be9eb8e9ca5 |
completed | May 11, 2026, 9:28 a.m. |
Created at: May 1, 2026, 1:59 a.m.