Triple
T26836278
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fort Carroll (site) |
E675639
|
entity |
| Predicate | protectsApproachTo |
P165369
|
FINISHED |
| Object | Port of Baltimore |
—
|
NE NERFINISHED |
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: Port of Baltimore | Statement: [Fort Carroll (site), protectsApproachTo, Port of Baltimore]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: protectsApproachTo Context triple: [Fort Carroll (site), protectsApproachTo, Port of Baltimore]
-
A.
hasApproachRoad
Indicates that one entity is connected to or accessed by another entity via an approach road leading to it.
-
B.
guardedApproachTo
Indicates a cautious, defensive, or wary manner of moving toward or engaging with another entity.
-
C.
approachControl
Indicates that one entity moves closer to another entity in a deliberate or controlled manner.
-
D.
usedToApproach
Indicates that one entity employed another entity as a means or method to move closer to or reach a target entity or location.
-
E.
hasApproachControl
Indicates that one entity exercises approach control authority or responsibility over another entity, typically managing its approach phase or access.
- 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_69eee9b776448190993a60b67fcc9545 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f658a91ba0819084fbe3dd8a09f7cd |
completed | May 2, 2026, 8:03 p.m. |
| PD | Predicate disambiguation | batch_69f6575ba12081909396036f78757a76 |
completed | May 2, 2026, 7:58 p.m. |
| PDg | Predicate description generation | batch_69f657f2c8b08190bfeb3173ef78207d |
completed | May 2, 2026, 8 p.m. |
Created at: April 27, 2026, 5:05 a.m.