Triple
T20855197
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Markale market shellings |
E513461
|
entity |
| Predicate | firstAttackDate |
P133671
|
FINISHED |
| Object | 1994-02-05 |
—
|
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: 1994-02-05 | Statement: [Markale market shellings, firstAttackDate, 1994-02-05]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstAttackDate Context triple: [Markale market shellings, firstAttackDate, 1994-02-05]
-
A.
firstKnownAttackDate
chosen
Indicates the date on which an entity’s earliest known attack or offensive action occurred.
-
B.
attackDate
Indicates the calendar date on which an attack or assault event took place.
-
C.
firstShotsFiredOn
Indicates that the referenced event or entity marks the initial occurrence of shots being fired on a specified date, time, or occasion.
-
D.
firstCombatUseDate
Indicates the date on which something (typically a weapon, system, or tactic) was first used in actual combat.
-
E.
firstShotsFiredAt
Indicates the location or time at which the initial gunshots or opening fire in an incident occurred.
- 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_69e0b4f5b01081909452f654d2fc3f50 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c3a7113c819087994bcdfe643bc1 |
completed | April 21, 2026, 12:24 a.m. |
| PD | Predicate disambiguation | batch_69e5c9a593f481908beb457c29f1ce73 |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:44 p.m.