Triple
T23497300
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FTTH |
E571735
|
entity |
| Predicate | locatedAtCentralOffice |
P18768
|
FINISHED |
| Object | OLT |
—
|
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: OLT | Statement: [FTTH, locatedAtCentralOffice, OLT]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedAtCentralOffice Context triple: [FTTH, locatedAtCentralOffice, OLT]
-
A.
locatedOff
Indicates that one entity is situated away from, but in the vicinity of, another entity or reference point, rather than directly on or within it.
-
B.
locatedInOrganizationally
Indicates that one entity is organizationally situated within, or belongs to, another entity in terms of administrative or structural hierarchy.
-
C.
isCentralHubOf
Indicates that one entity functions as the primary connecting or coordinating hub for activities, resources, or interactions among multiple other entities.
-
D.
notLocatedAt
Indicates that an entity is explicitly not situated, present, or found at a specified location.
-
E.
centralLocation
chosen
Indicates that one entity serves as the primary or central place associated with another entity.
- 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_69e245b4829881909b77a70e942bbd54 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a7e0c5a48190badb8303f40f6180 |
completed | April 29, 2026, 6:40 a.m. |
| PD | Predicate disambiguation | batch_69f0621165c08190a0b27b1319733959 |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 17, 2026, 6:05 p.m.