Triple
T37220753
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portland Road |
E922872
|
entity |
| Predicate | openingCompany |
P109322
|
FINISHED |
| Object | Metropolitan Railway |
—
|
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: Metropolitan Railway | Statement: [Portland Road, openingCompany, Metropolitan Railway]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: openingCompany Context triple: [Portland Road, openingCompany, Metropolitan Railway]
-
A.
isOpenCompany
Indicates that a company operates with open, transparent, and collaborative practices, such as sharing information, decision-making, or resources publicly or with stakeholders.
-
B.
hasOpeningCompany
chosen
Indicates that one entity is the company responsible for opening, initiating, or starting the other entity (such as an account, contract, or process).
-
C.
openingByOffice
Indicates that an office or administrative unit is responsible for initiating or formally opening something (such as a case, process, or record).
-
D.
openingName
Indicates the name or title assigned to a specific opening, such as an initial move, phase, or starting configuration in a structured sequence or activity.
-
E.
openingSettingOf
Indicates that one entity serves as the initial or first setting/location in which the other entity begins or is introduced.
- 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_69f76ea6f5288190b8d9988f613811c0 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fd553d7cb881908d243e7a9f30ac85 |
completed | May 8, 2026, 3:15 a.m. |
| PD | Predicate disambiguation | batch_69fd514dcb1c81908333c70d7edd79c9 |
completed | May 8, 2026, 2:58 a.m. |
Created at: May 3, 2026, 4:15 p.m.