Triple
T30656965
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ziad Jarrah |
E780410
|
entity |
| Predicate | positionAmongHijackersOnFlight |
P196179
|
FINISHED |
| Object | pilot hijacker |
—
|
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: pilot hijacker | Statement: [Ziad Jarrah, positionAmongHijackersOnFlight, pilot hijacker]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionAmongHijackersOnFlight Context triple: [Ziad Jarrah, positionAmongHijackersOnFlight, pilot hijacker]
-
A.
numberOfHijackers
Indicates the quantity of individuals who carried out or attempted to carry out a hijacking in the described event or context.
-
B.
positionOnFlight
Indicates the specific seat or positional assignment that an entity has on a particular flight.
-
C.
positionAtAirline
Indicates that an entity holds a specific role or job position within a particular airline.
-
D.
casualtiesHijackers
Indicates that the hijackers caused or were responsible for casualties (deaths or injuries) among others.
-
E.
passengers
Indicates that one entity is traveling in or being transported by another entity, typically as a non-operating occupant.
- 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_69f224a6d10481909290be1a00fc83b3 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fe12a899d4819080d48423f32eace9 |
completed | May 8, 2026, 4:43 p.m. |
| PD | Predicate disambiguation | batch_69fe0d7f6aa08190a1d2dfc025d4e0dc |
completed | May 8, 2026, 4:21 p.m. |
| PDg | Predicate description generation | batch_69fe12a769c08190bc445d302d2e8f98 |
completed | May 8, 2026, 4:43 p.m. |
Created at: April 29, 2026, 8:30 p.m.