Triple
T29149492
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas Schiff |
E738863
|
entity |
| Predicate | heldAtGunpointBy |
P166368
|
FINISHED |
| Object | Harvey Dent |
—
|
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: Harvey Dent | Statement: [Thomas Schiff, heldAtGunpointBy, Harvey Dent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heldAtGunpointBy Context triple: [Thomas Schiff, heldAtGunpointBy, Harvey Dent]
-
A.
heldCaptive
Indicates that one entity is being forcibly confined or restrained by another, preventing their freedom of movement or escape.
-
B.
heldHostagesFor
Indicates that one party unlawfully detained another party or parties as hostages for a period of time, typically to exert pressure or gain leverage.
-
C.
takesHostageDuring
Indicates that one entity seizes and holds another entity as a hostage in the course of a particular event or action.
-
D.
heldToProtect
Indicates that one entity is kept in someone’s possession or custody for the purpose of safeguarding or protecting it.
-
E.
heldTo
Indicates that one entity is obligated, bound, or accountable to another entity, standard, or agreement.
- 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_69f07cb46f148190874eb8576a447567 |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f662a439c88190985b014077e75ecc |
completed | May 2, 2026, 8:46 p.m. |
| PD | Predicate disambiguation | batch_69f65c2376a08190be5215171e908e69 |
completed | May 2, 2026, 8:18 p.m. |
| PDg | Predicate description generation | batch_69f65f75ac608190a62cd6afce14f68e |
completed | May 2, 2026, 8:32 p.m. |
Created at: April 28, 2026, 11:41 a.m.