Triple
T27529463
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fort Michie |
E694926
|
entity |
| Predicate | protectsApproachesTo |
P165369
|
FINISHED |
| Object | New York Harbor |
—
|
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: New York Harbor | Statement: [Fort Michie, protectsApproachesTo, New York Harbor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: protectsApproachesTo Context triple: [Fort Michie, protectsApproachesTo, New York Harbor]
-
A.
protectsApproachTo
chosen
Indicates that one entity safeguards or defends the way or route by which another entity is accessed or approached.
-
B.
protectedApproach
Indicates that one entity safeguards, supports, or enables another entity’s method, path, or manner of proceeding so it can be carried out safely or without interference.
-
C.
guardedApproachTo
Indicates a cautious, defensive, or wary manner of moving toward or engaging with another entity.
-
D.
providesProtectionAgainst
Indicates that one entity serves to guard, shield, or defend another entity from a specified harm, threat, or adverse effect.
-
E.
protects
Indicates taking action to keep someone or something safe from harm, danger, or negative effects.
- 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_69ef538608b081908b9f659bb09d5e0f |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f6640168948190811bd5f933a87cf5 |
completed | May 2, 2026, 8:52 p.m. |
| PD | Predicate disambiguation | batch_69f6633451948190bcc0410602bb4914 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 27, 2026, 1:25 p.m.