Triple
T25509893
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MBTA Green Line main line |
E639345
|
entity |
| Predicate | isTrunkFor |
P110868
|
FINISHED |
| Object | MBTA Green Line branches |
—
|
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: MBTA Green Line branches | Statement: [MBTA Green Line main line, isTrunkFor, MBTA Green Line branches]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isTrunkFor Context triple: [MBTA Green Line main line, isTrunkFor, MBTA Green Line branches]
-
A.
isOnTrunkLine
chosen
Indicates that something is located on, or directly connected to, a primary or main trunk line within a network or system.
-
B.
hasTrunk
Indicates that one entity possesses or is equipped with a trunk as a physical feature or component.
-
C.
supportsTrunks
Indicates that one entity provides structural or functional support to the trunks of another entity.
-
D.
trunkSymbolizes
Indicates that a trunk (such as that of a tree, elephant, or container) serves as a symbol or representation of some concept, quality, or entity.
-
E.
hasTrunkCarvings
Indicates that an entity (typically a tree) possesses carvings or engravings on its trunk.
- 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_69e75dbd09308190b6b5f0afdc12ec6d |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f809726081908ae4122cd4e581c1 |
completed | May 2, 2026, 1:11 p.m. |
| PD | Predicate disambiguation | batch_69f468421ba08190880eac99135e5970 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 21, 2026, 2:48 p.m.