Triple
T1906607
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Actium |
E38018
|
entity |
| Predicate | hasAncientHarbor |
P3007
|
FINISHED |
| Object | harbor facing the Ambracian Gulf |
—
|
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: harbor facing the Ambracian Gulf | Statement: [Actium, hasAncientHarbor, harbor facing the Ambracian Gulf]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAncientHarbor Context triple: [Actium, hasAncientHarbor, harbor facing the Ambracian Gulf]
-
A.
hasHarbor
chosen
Indicates that a place possesses or contains a harbor for docking or sheltering vessels.
-
B.
hasPrivateHarbour
Indicates that an entity possesses or is associated with its own exclusive harbour not shared with the general public.
-
C.
hasHarborOpened
Indicates that a harbor has been officially opened and is available for use or operation.
-
D.
hasMaritimeHeritage
Indicates that an entity possesses a historical, cultural, or traditional connection to maritime activities, seafaring, or the sea.
-
E.
locatedInAncientCity
Indicates that an entity is situated within the boundaries or domain of an ancient city.
- 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_69a8862a26088190aae5243695aeefc0 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb34d94fc8190a5bf1e582c77c725 |
completed | March 7, 2026, 5:10 a.m. |
| PD | Predicate disambiguation | batch_69abafe9f8b0819086d8f6288511c66d |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:35 p.m.