Triple
T38180333
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bellows Falls Tunnel |
E1005139
|
entity |
| Predicate | hasClearanceRestriction |
P196200
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Bellows Falls Tunnel, hasClearanceRestriction, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasClearanceRestriction Context triple: [Bellows Falls Tunnel, hasClearanceRestriction, true]
-
A.
hasClearance
Indicates that one entity possesses the required authorization level or permission to access or perform actions on another entity or resource.
-
B.
hasClearanceType
Indicates that an entity possesses a specific level or category of authorized access or security clearance.
-
C.
hasClearanceOver
Indicates that one entity possesses authorized access rights or control privileges over another entity or resource.
-
D.
hasClearanceBelow
Indicates that one entity’s clearance level is lower than another entity’s clearance level.
-
E.
hasHumanUseRestriction
Indicates that there is a limitation or condition on how something may be used by humans.
- 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_69f76dbc22c481908139b694ffde7a0c |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fe12a899d4819080d48423f32eace9 |
completed | May 8, 2026, 4:43 p.m. |
| PD | Predicate disambiguation | batch_69fe0d7f6aa08190a1d2dfc025d4e0dc |
completed | May 8, 2026, 4:21 p.m. |
| PDg | Predicate description generation | batch_69fe12a769c08190bc445d302d2e8f98 |
completed | May 8, 2026, 4:43 p.m. |
Created at: May 3, 2026, 4:29 p.m.