Triple
T28470851
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | STS-1 |
E720431
|
entity |
| Predicate | hasPathOverhead |
P191783
|
FINISHED |
| Object | SONET path overhead |
—
|
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: SONET path overhead | Statement: [STS-1, hasPathOverhead, SONET path overhead]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPathOverhead Context triple: [STS-1, hasPathOverhead, SONET path overhead]
-
A.
hasLineOverhead
Indicates that one entity has an overhead line (such as a cable, wire, or similar linear infrastructure) positioned above it or running over it.
-
B.
hasOverheadType
Indicates that one entity is associated with a specific category or type of overhead (such as cost, resource, or operational overhead) that applies to it.
-
C.
overheadComparedToTCP
Indicates the additional protocol or processing cost incurred by something relative to using TCP as the baseline.
-
D.
supportsPathLengthUpTo
Indicates that an entity can accommodate or function correctly with paths whose length does not exceed a specified maximum value.
-
E.
typicalOverhead
Indicates the usual or expected amount of additional cost, time, or resource usage associated with performing an action or maintaining a relationship.
- 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_69f01a5983f48190b7c1b8857245a4f7 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69fcec5f8b448190b48330a19b462d24 |
completed | May 7, 2026, 7:47 p.m. |
| PD | Predicate disambiguation | batch_69fceaf1e23881908ca24160a638e329 |
completed | May 7, 2026, 7:41 p.m. |
| PDg | Predicate description generation | batch_69fcec5e560481909cd710b88897e833 |
completed | May 7, 2026, 7:47 p.m. |
Created at: April 28, 2026, 2:48 a.m.