Triple
T12123175
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris Agreements on the status of the Federal Republic of Germany |
E288742
|
entity |
| Predicate | signingDateApproximate |
P877
|
FINISHED |
| Object | October 1954 |
—
|
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: October 1954 | Statement: [Paris Agreements on the status of the Federal Republic of Germany, signingDateApproximate, October 1954]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: signingDateApproximate Context triple: [Paris Agreements on the status of the Federal Republic of Germany, signingDateApproximate, October 1954]
-
A.
dateSigned
Indicates the specific date on which an agreement, document, or contract was formally signed.
-
B.
agreementSignedAt
Indicates the specific time and/or place at which an agreement was formally signed.
-
C.
signaturesTargetDate
Indicates the date by which the required signatures are expected to be obtained or completed.
-
D.
dateApproximate
chosen
Indicates that the associated date is not exact but estimated or approximate rather than precisely known.
-
E.
openingDateApproximate
Indicates that the date when something was opened or began is not known exactly and is only an approximate value.
- 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_69d6ab4b5e4c81909950b17151eb0951 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d91841615c819097f20a7447a1b8f4 |
completed | April 10, 2026, 3:33 p.m. |
| PD | Predicate disambiguation | batch_69d91508f8008190b3a90ec0bf0953ca |
completed | April 10, 2026, 3:19 p.m. |
Created at: April 8, 2026, 9:49 p.m.