Triple
T24519780
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amine Gemayel |
E606487
|
entity |
| Predicate | presidencyContext |
P70434
|
FINISHED |
| Object | Lebanese Civil War |
—
|
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: Lebanese Civil War | Statement: [Amine Gemayel, presidencyContext, Lebanese Civil War]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: presidencyContext Context triple: [Amine Gemayel, presidencyContext, Lebanese Civil War]
-
A.
presidency
Indicates that an entity holds or relates to the office, role, or term of serving as president over a state, organization, or institution.
-
B.
presidencyNature
Indicates the type or character of a presidency, such as its style, structure, or defining institutional features, in relation to a given office or term.
-
C.
partOfPresidency
chosen
Indicates that an event, action, or role occurred during and within the scope of a specific individual's term in office as president.
-
D.
presidencyHeldBy
Indicates that a specific presidency or presidential office is occupied or held by a particular person.
-
E.
presidencyReservedFor
Indicates that the position of presidency is restricted or set aside exclusively for a specific person, group, or category of entities.
- 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_69e2c4c85778819085f5da9af3569ad5 |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2be044d4c819094e14eda28d371a7 |
completed | April 30, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f2a6b0ca8081908d931aec560eae56 |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:24 a.m.