Triple
T1196976
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | My Lai massacre |
E25688
|
entity |
| Predicate | sentenceModification |
P25699
|
FINISHED |
| Object | reduced to house arrest |
—
|
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: reduced to house arrest | Statement: [My Lai massacre, sentenceModification, reduced to house arrest]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sentenceModification Context triple: [My Lai massacre, sentenceModification, reduced to house arrest]
-
A.
sentence
Indicates that one entity is a sentence that expresses, contains, or encodes information about another entity.
-
B.
lexicalChange
Indicates a relationship where one linguistic form is replaced, modified, or evolves into another form over time or across language varieties.
-
C.
leafModification
Indicates a relationship where an entity undergoes or causes a change in the structure, form, or characteristics of a leaf.
-
D.
sentenceType
Indicates the classification of a sentence according to its communicative function or structural type (e.g., question, statement, command).
-
E.
sentenceOf
Indicates that one entity is a sentence that belongs to, is contained in, or is part of another larger text or document.
- F. None of above. chosen
Provenance (4 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_69a49429f5ec8190a6a205eb0ae81e5e |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bd9a305c819091513394f1b67784 |
completed | March 1, 2026, 10:28 p.m. |
| PD | Predicate disambiguation | batch_69a4bb5d40a08190b7682d8ef8075421 |
completed | March 1, 2026, 10:19 p.m. |
| PDg | Predicate description generation | batch_69a4bc49693c8190978ec63a5171d342 |
completed | March 1, 2026, 10:23 p.m. |
Created at: March 1, 2026, 7:46 p.m.