Triple
T539813
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fort Devens, Massachusetts |
E12604
|
entity |
| Predicate | closedAsActiveArmyPost |
P16659
|
FINISHED |
| Object | 1996 |
—
|
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: 1996 | Statement: [Fort Devens, Massachusetts, closedAsActiveArmyPost, 1996]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: closedAsActiveArmyPost Context triple: [Fort Devens, Massachusetts, closedAsActiveArmyPost, 1996]
-
A.
closed
Indicates that an entity has brought something (such as an object, container, or space) from an open state into a shut or sealed state, or that it is currently in that shut state.
-
B.
closedIn
Indicates that one entity is enclosed, contained, or surrounded within the boundaries or limits defined by another entity.
-
C.
closedDuring
Indicates that an entity is not open or available for use during a specified time period or under certain conditions.
-
D.
militaryStatus
Indicates the relationship between an entity and a military organization in terms of service condition, such as active duty, reserve, veteran, or non-military status.
-
E.
garrisonAfterWar
Indicates that a military force is stationed in or occupies a location following the end of a war or major conflict.
- 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_69a49334226c81908b0ea1689ef6aa3f |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4985e51908190a34aa82ea9dbee1e |
completed | March 1, 2026, 7:49 p.m. |
| PD | Predicate disambiguation | batch_69a494b67c308190a1a225ab7c4b74c6 |
completed | March 1, 2026, 7:34 p.m. |
| PDg | Predicate description generation | batch_69a49857e1148190aa782b82675cf0b5 |
completed | March 1, 2026, 7:49 p.m. |
Created at: March 1, 2026, 7:32 p.m.