Triple
T17796078
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shenzhen Metro Line 3 |
E444294
|
entity |
| Predicate | hasExtensionOpeningYear |
P105509
|
FINISHED |
| Object | 2011 |
—
|
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: 2011 | Statement: [Shenzhen Metro Line 3, hasExtensionOpeningYear, 2011]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasExtensionOpeningYear Context triple: [Shenzhen Metro Line 3, hasExtensionOpeningYear, 2011]
-
A.
hasExtensionOpeningDate
Indicates that an entity has an associated opening date specifically for an extension or expansion of it.
-
B.
extensionOpeningYear
chosen
Indicates the year in which an extension to an existing entity (such as a building, line, or service) was officially opened or put into operation.
-
C.
officialOpeningYear
Indicates the calendar year in which something was formally opened or inaugurated for official use.
-
D.
extensionOpeningPeriod
Indicates the time span during which an extension (such as a facility, service, or feature) is open or available for use.
-
E.
mostRecentExpansionYear
Indicates the calendar year in which the entity most recently underwent an expansion.
- 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_69d8b9efe370819095cd219b143ae727 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e487fafc2c8190b28e791267c47e3c |
completed | April 19, 2026, 7:44 a.m. |
| PD | Predicate disambiguation | batch_69e3d8de28688190844b65acf6af54e6 |
completed | April 18, 2026, 7:17 p.m. |
Created at: April 10, 2026, 10:13 a.m.