Triple
T589158
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Beiping–Tianjin |
E17227
|
entity |
| Predicate | dateOfJapaneseCaptureOfTianjin |
P10180
|
FINISHED |
| Object | 1937-07-30 |
—
|
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: 1937-07-30 | Statement: [Battle of Beiping–Tianjin, dateOfJapaneseCaptureOfTianjin, 1937-07-30]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dateOfJapaneseCaptureOfTianjin Context triple: [Battle of Beiping–Tianjin, dateOfJapaneseCaptureOfTianjin, 1937-07-30]
-
A.
dateOfCityCapture
chosen
Indicates the specific date on which a city was taken or captured, typically in a military or political context.
-
B.
dateOfTokyoBayPresence
Indicates the specific date on which an entity was present in Tokyo Bay.
-
C.
dateOfCityEncirclement
Indicates the date on which a city became fully encircled, typically by military or blockade forces, cutting it off from external access.
-
D.
invasionDate
Indicates the date on which an invasion event occurred or began.
-
E.
dateOfParisOccupation
Indicates the date on which the occupation of Paris by a particular force or authority began.
- 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_69a49379d09c8190ac7e00b24e2810b1 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49bb775fc819085b968f8615dca59 |
completed | March 1, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69a494cc13988190892ca10bd7ae9f09 |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:33 p.m.