Triple
T36453919
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | M98 |
E898098
|
entity |
| Predicate | lockingLugs |
P167701
|
FINISHED |
| Object | two front locking lugs |
—
|
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: two front locking lugs | Statement: [M98, lockingLugs, two front locking lugs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lockingLugs Context triple: [M98, lockingLugs, two front locking lugs]
-
A.
boltLockingLugs
chosen
Indicates that one entity serves as the locking lugs on a bolt that mechanically secure it in place during operation.
-
B.
locks
Indicates that one entity secures, fastens, or restricts access to another entity, typically preventing its use or opening without proper authorization or a key.
-
C.
lockedMeans
Indicates that one state, condition, or action guarantees or necessitates another, such that when the first is "locked in," the second must follow.
-
D.
lock
Indicates that an entity secures or fastens another entity so that it cannot be opened, accessed, or changed without authorization.
-
E.
lockConnects
Indicates that one lock or locking mechanism is physically or functionally connected to another component, enabling it to secure, release, or interface with that component.
- 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_69f76e57f08481908593bd0bc34581c8 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7be9d07ac8190adf796cbef60daf6 |
completed | May 3, 2026, 9:31 p.m. |
| PD | Predicate disambiguation | batch_69f7bccf05bc8190b61fdb2b2a315811 |
completed | May 3, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:10 p.m.