Triple
T24015530
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Asal Uttar |
E594661
|
entity |
| Predicate | IndianEquipmentUsed |
P2728
|
FINISHED |
| Object | Sherman tanks |
—
|
NE NERFINISHED |
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: Sherman tanks | Statement: [Battle of Asal Uttar, IndianEquipmentUsed, Sherman tanks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: IndianEquipmentUsed Context triple: [Battle of Asal Uttar, IndianEquipmentUsed, Sherman tanks]
-
A.
usedItem
Indicates that an entity has utilized or employed a particular item for some purpose.
-
B.
usedInECommerce
Indicates that something is employed or applied within the context of electronic commerce activities or systems.
-
C.
hardwareUsedBy
Indicates that a piece of hardware is utilized or operated by a particular entity (such as a person, system, or organization).
-
D.
usesEquipment
chosen
Indicates that an entity employs or operates a particular piece of equipment to perform an action or fulfill a function.
-
E.
usedEquipmentFrom
Indicates that one entity has utilized or operated equipment that originated from or was provided by another entity.
- 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_69e288bc8f608190ac4af29f0bd1c744 |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1d5a32374819094dcb42abf18c033 |
completed | April 29, 2026, 9:55 a.m. |
| PD | Predicate disambiguation | batch_69f17639d23c8190bed93434e2f9230a |
completed | April 29, 2026, 3:08 a.m. |
Created at: April 17, 2026, 9:42 p.m.