Triple
T21083896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U.S. Embassy in Tehran |
E519438
|
entity |
| Predicate | hostageCrisisEnd |
P131649
|
FINISHED |
| Object | 1981-01-20 |
—
|
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: 1981-01-20 | Statement: [U.S. Embassy in Tehran, hostageCrisisEnd, 1981-01-20]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hostageCrisisEnd Context triple: [U.S. Embassy in Tehran, hostageCrisisEnd, 1981-01-20]
-
A.
hostageOutcome
chosen
Indicates the result or final status of a hostage situation, such as whether hostages were released, rescued, harmed, or remained captive.
-
B.
grantedHostages
Indicates that one party has given or handed over hostages to another party, typically as a guarantee or security in an agreement or conflict.
-
C.
hostages
Indicates that one party is forcibly holding another party captive, typically to compel a third party to meet certain demands or conditions.
-
D.
hostagePower
Indicates that one entity exerts power or leverage over another by holding someone or something important to that other entity as a hostage.
-
E.
takesHostageDuring
Indicates that one entity seizes and holds another entity as a hostage in the course of a particular event or action.
- 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_69e0b507dd9081908fb8bfcbef4c8b46 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e70948704481908b8b75a2ecc42bb6 |
completed | April 21, 2026, 5:21 a.m. |
| PD | Predicate disambiguation | batch_69e5dbfcd5e881908f1e4e0d2d237856 |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 2:49 p.m.