Triple
T21847663
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charpennes – Charles Hernu |
E539416
|
entity |
| Predicate | lineAOpeningDate |
P145547
|
FINISHED |
| Object | 1978 |
—
|
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: 1978 | Statement: [Charpennes – Charles Hernu, lineAOpeningDate, 1978]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lineAOpeningDate Context triple: [Charpennes – Charles Hernu, lineAOpeningDate, 1978]
-
A.
lineSectionOpeningDate
Indicates the date on which a specific section of a line (e.g., a route, track, or corridor) was officially opened for use.
-
B.
line2OpeningDate
Indicates the date on which the second line (e.g., a route, service, or facility line) was officially opened or began operation.
-
C.
line4OpeningDate
Indicates the date on which the fourth line (e.g., of a transit system or network) was officially opened or began operation.
-
D.
line3OpeningDate
Indicates the calendar date on which the third line (e.g., a route, service line, or similar system component) was officially opened or began operation.
-
E.
line8OpeningDate
Indicates the date on which line 8 was first opened or began operation.
- 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_69e0c476c3c88190a92d08ebb59a128a |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f0bd558ed88190a10b8d6752105cd6 |
completed | April 28, 2026, 1:59 p.m. |
| PD | Predicate disambiguation | batch_69e6be8c14748190bdcc44a14d50bea4 |
completed | April 21, 2026, 12:02 a.m. |
| PDg | Predicate description generation | batch_69e6c187bc548190b4ca13150f6bae38 |
completed | April 21, 2026, 12:15 a.m. |
Created at: April 16, 2026, 6:55 p.m.