Triple
T141012
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Singapore |
E2848
|
entity |
| Predicate | typeOfEngagement |
P3663
|
FINISHED |
| Object | siege and urban battle |
—
|
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: siege and urban battle | Statement: [Battle of Singapore, typeOfEngagement, siege and urban battle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfEngagement Context triple: [Battle of Singapore, typeOfEngagement, siege and urban battle]
-
A.
engagementType
chosen
Indicates the specific kind or category of engagement or interaction that occurs between the related entities.
-
B.
engagementLevel
Indicates the degree or intensity of involvement, interest, or participation one entity has in relation to another entity, activity, or context.
-
C.
notableEngagement
Indicates a significant interaction, involvement, or participation between entities that is noteworthy or distinguished in some context.
-
D.
participation
Indicates that an entity takes part in, contributes to, or is involved in a shared activity, event, or process with others.
-
E.
agingPotential
Indicates the capacity or suitability of something to improve, develop, or remain effective over time as it ages.
- 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_69a2521e35c08190b28e5c9f1e3c9b59 |
completed | Feb. 28, 2026, 2:25 a.m. |
| NER | Named-entity recognition | batch_69a2580ca15481909fa3e87d804a1b23 |
completed | Feb. 28, 2026, 2:50 a.m. |
| PD | Predicate disambiguation | batch_69a2565559ac81909e0c4e095a7dfa27 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:31 a.m.