Triple
T14607695
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Halabja |
E342873
|
entity |
| Predicate | attackChemicalAgentsUsed |
P820
|
FINISHED |
| Object | mustard gas |
—
|
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: mustard gas | Statement: [Halabja, attackChemicalAgentsUsed, mustard gas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: attackChemicalAgentsUsed Context triple: [Halabja, attackChemicalAgentsUsed, mustard gas]
-
A.
destroyedChemicalAgent
Indicates that an entity has rendered a chemical agent unusable or eliminated it, typically through neutralization, dismantling, or disposal.
-
B.
chemicalWeaponUseContext
Indicates the situational circumstances or conditions under which a chemical weapon is used.
-
C.
usedAsWarheadFor
Indicates that something functions as the explosive or destructive payload component for a specified weapon or delivery system.
-
D.
usResponseToChemicalWeapons
Indicates the actions, policies, or measures taken by the United States in reaction to the use, threat, or proliferation of chemical weapons.
-
E.
weaponsUsed
chosen
Indicates that one entity employed or utilized another entity as a weapon in carrying out an action or event.
- 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_69d822dec68081908c2553145c4051dc |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb44d327c8190a8d20568429d0f80 |
completed | April 14, 2026, 9:40 p.m. |
| PD | Predicate disambiguation | batch_69de656f9f4c81909f815b6629a9ee39 |
completed | April 14, 2026, 4:03 p.m. |
Created at: April 10, 2026, 1:25 a.m.